215 accepted papers
Magnetic microrobots hold great promise for biomedical applications. However, achieving flexible magnetic field adjustment with a magnetic actuation system (MAS) to actuate diverse microrobots remains a significant challenge. In this work, we propose an Electromagnetic-Permanent Magnet Actuation (EP…
Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to use tools for verification, limiting their reliability on complex multimodal reasoning tasks.We present **ARM-Thinker**
Recent advances in text-to-image (T2I) generation can produce highly resembling images of copyrighted characters, often indistinguishable from official depictions, raising serious concerns about intellectual property infringement. Consequently, robust detection of copyright character infringement is
Electroencephalogram (EEG) signals have unique individual characteristics and have broad application prospects in identity authentication. At present, person identification (PI) based on EEG using the temporal-spatial-spectral feature extraction framework has achieved remarkable success. However, th…
Remote sensing change detection (RSCD) aims to identify changed regions in bitemporal images. However, conventional one-step modeling suffers from performance degradation caused by imaging temporal differences (e.g., illumination disturbances, seasonal variations). To address this issue, we formulat
Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to reduce computational cost. However, these methods fail to achie…
Vision-and-Language Navigation (VLN) requires agents to follow long-horizon instructions and navigate complex 3D environments. However, existing approaches face two major challenges: constructing an effective long-term memory bank and overcoming the compounding errors problem. To address these issue
Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial computational overhead, hindering real-world deployment. Accelerating diffusion models is therefore essential, yet determining how to combine
Multi-view video reconstruction plays a vital role in computer vision, enabling applications in film production, virtual reality, and motion analysis. While recent advances such as 3D Gaussian Splatting have demonstrated impressive capabilities in dynamic scene reconstruction, they typically rely on
Tool-augmented language model agents have shown great potential in solving complex real-world tasks, but a key challenge remains balancing planning flexibility with the reliability required for production deployment. Existing approaches either execute tools sequentially without parallelism or genera…
Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP perform well on global alignment, they often struggle to capture…
Dark optical flow estimation (DOFE) faces critical challenges: discriminative models are less robust to noise and struggle with weakened motion patterns, while diffusion models suffer from discontinuous flow fields and low efficiency. Flow matching (FM), though efficient, remains underexplored for c
Vision-and-Language Navigation (VLN) empowered by Multimodal Large Language Models (MLLMs) is promise, yet remains challenged by long-horizon tasks with complex user instructions. Existing approaches that continuously condition on full instructions incur high latency due to abundant visual tokens an…
Large Language Models (LLMs) have shown remarkable success on a wide range of math and reasoning benchmarks. However, we observe that they often struggle when faced with unreasonable math problems. Instead of recognizing these issues, models frequently proceed as if the problem is well-posed, produc
While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), typically apply coarse-grained optimiz…
This paper presents Reed-Solomon coded single-stranded representation learning (RSRL), a novel end-to-end model for learning representations for lossless DNA data storage. In contrast to existing learning-based methods, RSRL is inspired by both error-correction codec and structural biology. Specific
A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we present MM-ACT, a unified Vision-Language-Action (VLA) model that integrates text, image, and action in shared token sp
Reconstructing dynamic 3D scenes with photorealistic detail and temporal coherence remains a significant challenge. Existing Gaussian splatting approaches modeling scenes rely on per-frame optimization, causing them to overfit to instantaneous states rather than learning true motion dynamics. To add…
The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks. However, the scarcity of diverse CoaT trajectories limits the expressiveness and generalization ability of such agents. While self-training is commonly e…
SQL injection remains a major threat to web applications, as existing defenses often fail against obfuscation and evolving attacks because of neglecting the request-response context. This paper presents a context-enriched SQL injection detection framework, focusing on constructing a high-quality req…
Document AI has advanced rapidly and is attracting increasing attention. Yet, while most efforts have focused on document layout analysis (DLA), its generative counterpart, layout generation, remains underexplored. Distinct from traditional graphic layout design and room layout planning, document la
AI-generated text increasingly blends with human writing, raising practical risks such as misinformation, academic misuse, and corpora contamination. While statistical detectors are appealing for efficiency and generalization, they suffer from two key limitations. (i) Boilerplate dominance, boilerpl…
Recent advancements in reasoning language models have fueled growing interest in extending such capabilities to multimodal domains. However, despite notable progress in visual and video reasoning, the lack of transparent and reproducible data curation and training pipelines remains a major barrier t
Joint optimization of pricing, dispatching, and routing is critical for hub-based mobility services but challenging due to complex decision couplings and strict service guarantees, such as Order Response Rate (ORR). Conventional constrained reinforcement learning often struggles in this mixed contin
Semantic-level watermarking (SWM) for large language models (LLMs) enhances watermarking robustness against text modifications and paraphrasing attacks by treating the sentence as the fundamental unit. However, existing methods still lack strong theoretical guarantees of robustness, and reject-sampl…
Source-Free Domain Adaptation (SFDA) enables domain adaptation for semantic segmentation of Remote Sensing Images (RSIs) using only a well-trained source model and unlabeled target domain data. However, the lack of ground-truth labels in the target domain often leads to the generation of noisy pseud…
Data selection for instruction tuning is crucial for improving the performance of large language models (LLMs) while reducing training costs. In this paper, we propose Refined Contribution Measurement with In-Context Learning (RICo), a novel gradient-free method that quantifies the fine-grained cont
Visual manipulation localization (VML) aims to identify tampered regions in images and videos, a task that has become increasingly challenging with the rise of advanced editing tools. Existing methods face two main issues: resolution diversity, where resizing or padding distorts forensic traces and…
Neural Speech Codecs face a fundamental trade-off at low bitrates: preserving acoustic fidelity often compromises semantic richness. To address this, we introduce SACodec, a novel codec built upon an asymmetric dual-quantizer that employs our proposed Semantic Anchoring mechanism. This design strate
Event linking aims to associate event mentions in text with their corresponding entries in a knowledge base (KB). This task can help text understanding to benefit downstream tasks (e.g., question answering) and expand the KB through new event knowledge mentioned in the text. Existing event linking a
Functional brain network analysis plays an important role in understanding and diagnosing psychiatric disorders. However, current methods struggle with subject variations, impairing the model’s generalization ability to the test set. To address this issue, we propose the Subject Invariance-aware Inv…
VLM-based mobile agents are increasingly popular due to their capabilities to interact with smartphone GUIs and XML-structured texts and to complete daily tasks. However, existing online benchmarks fail to obtain stable critical reward signals under dynamic environmental changes, and neglect the inf…
Learnable sparse retrieval (LSR) models encode texts into high-dimensional sparse representations, supporting token-level expansion beyond the original text and addressing the vocabulary mismatch problem in traditional bag-of-words retrieval. However, in the absence of representation-level supervisi
Look-Up Table based methods have emerged as a promising direction for efficient image restoration tasks. Recent LUT-based methods focus on improving their performance by expanding the receptive field. However, they inevitably introduce extra computational and storage overhead, which hinders their de
Large vision–language models (VLMs) excel at multimodal understanding but fall short when extended to embodied tasks, where instructions must be transformed into low-level motor actions. We introduce SP-VLA, a dual-system **V**ision–**L**anguage–**A**ction framework that leverages **S**patial **P**r…
Diffusion models achieve strong generative performance but remain slow at inference due to the need for repeated full-model denoising passes. We present Token-Adaptive Predictor (TAP), a training-free, probe-driven framework that adaptively selects a predictor for each token at every sampling step.
Large language models (LLMs) have demonstrated remarkable capabilities in function calling for autonomous agents, yet current mechanisms lack explicit reasoning transparency during parameter generation, particularly for complex functions with interdependent parameters. While existing approaches like…
Table recognition (TR) aims to transform table images into semi-structured representations such as HTML or Markdown.As a core component of document parsing, TR has long relied on supervised learning, with recent efforts dominated by fine-tuning vision-language models (VLMs) using labeled data.While
Deep Reinforcement Learning agents are in- creasingly used in safety-critical domains but remain vulnerable to stealthy backdoor attacks. Existing outer-loop attacks face a trade-off be- tween perceptual stealth, poisoning efficiency, and value-function consistency, often making the at- tack ineffec…
With the widespread use of location-tracking technologies, large volumes of trajectory data are continuously generated. Trajectory similarity computation is a core task in trajectory mining with broad applications. However, existing methods still face two key challenges: (1) the difficulty of balanc
This paper introduces UniMERNet, a high-accuracy, computation-efficient algorithm for Mathematical Expression Recognition (MER) across diverse real-world scenarios. To facilitate UniMERNet's training, we constructed UniMER-1M, a million-scale dataset whose unprecedented diversity endows the model wi
To operate effectively in the real world, robots should integrate multimodal reasoning with precise action generation. However, existing vision-language-action (VLA) models often sacrifice one for the other, narrow their abilities to task-specific manipulation data, and suffer catastrophic forgettin…
Vascular interventional surgery (VIS) robots still face limitations in enhancing treatment quality. The primary challenges come from the accurate morphology control and miniaturization of the distal instruments. To address these issues, a novel 4 degrees of freedom steerable catheter robotic system
Diffusion models have gained attention for their success in modeling complex distributions, achieving impressive perceptual quality in SR tasks. However, existing diffusion-based SR methods often suffer from high computational costs, requiring numerous iterative steps for training and inference. Exi
We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs). It encompasses 8 distinct tasks and 26 datasets, among which, 7 are newly proposed datasets. The evaluation targets three main aspects: speech understanding, audio scene understanding, and vo…
At the core of Camouflaged Object Detection (COD) lies segmenting objects from their highly similar surroundings. Previous efforts navigate this challenge primarily through image-level modeling or annotation-based optimization. Despite advancing considerably, this commonplace practice hardly taps va…
Large Multi-modal Models (LMMs), trained on web-scale datasets predominantly composed of natural images, have demonstrated remarkable performance on general tasks. However, these models often exhibit limited specialized capabilities for domain-specific tasks that require extensive domain prior knowl…
Large Language Models (LLMs) have shown strong performance in solving mathematical problems, with code-based solutions proving particularly effective. However, the best practice to leverage coding instruction data to enhance mathematical reasoning remains underexplored. This study investigates three…
Despite Southeast Asia’s (SEA) extraordinary linguistic and cultural diversity, the region remains significantly underrepresented in vision-language (VL) research, resulting in AI models that inadequately capture SEA cultural nuances. To fill this gap, we present SEA-VL, an open-source initiative de…
Multivariate time series forecasting is a critical focus across many fields. Existing transformer-based models have overlooked the explicit modeling of inter-variable correlations. Similarly, the graph-based methods have also failed to address the dynamic nature of multivariate correlations and the
Low-light image enhancement methods based on diffusion models, though effective in improving image quality, often overrely on noise sensitivity and neglect the reconstruction deviations due to the naive up- and down-sampling operations. To address this issue, we propose a novel diffusion model, MWT-…
Video generative models can be regarded as world simulators due to their ability to capture dynamic, continuous changes inherent in real-world environments. These models integrate high-dimensional information across visual, temporal, spatial, and causal dimensions, enabling predictions of subjects i…
Event temporal reasoning (ETR) aims to model and reason about the relationships between events and time, as well as between events in the real world. Proficiency in ETR is a significant indicator that a large language model (LLM) truly understands the physical world. Previous question-answering data…
Visual tokens consume substantial computational resources in multi-modal large models (MLLMs), significantly compromising their efficiency. Recent works have attempted to improve efficiency by compressing visual tokens during training, either through modifications to model components or by introduci…
Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus on coarse-grained short captions. To address this, we propose Fine-Grained CLIP (FG-CLIP), which enhances…
Large language models (LLMs) have made significant strides in code translation tasks. However, ensuring both the correctness and readability of translated code remains a challenge, limiting their effective adoption in real-world software development. In this work, we propose F2STrans, a function-to…
Despite their proficiency in general tasks, Multi-modal Large Language Models (MLLMs) struggle with automatic Geometry Problem Solving (GPS), which demands understanding diagrams, interpreting symbols, and performing complex reasoning. This limitation arises from their pre-training on natural images…
An extensive high-quality instruction dataset is crucial for the instruction tuning process of Large Language Models (LLMs). Recent instruction expansion methods have demonstrated their capability to improve the quality and quantity of existing datasets, by prompting high-performance LLM to generate…
Many positional encodings (PEs) are designed to exhibit long-term decay, based on an entrenched and long-standing inductive opinion: tokens farther away from the current position carry less relevant information. We argue that long-term decay is outdated in the era of LLMs, as LLMs are now applied to…
Text-to-image generation models often struggle to interpret spatially aware text prompts effectively. To overcome this, existing approaches typically require millions of high-quality semantic layout annotations consisting of bounding boxes and regional prompts. This paper shows that the large amount…
In the field of multimodal large language models (MLLMs), common methods typically involve unfreezing the language model during training to foster profound visual understanding. However, the fine-tuning of such models with vision-language data often leads to a diminution of their natural language pr…
Formula recognition presents significant challenges due to the complicated structure and varied notation of mathematical expressions. Despite continuous advancements in formula recognition models, the evaluation metrics employed by these models, such as BLEU and Edit Distance, still exhibit notable…
The rapid advancements in generative technology have emerged as a double-edged sword. While offering powerful tools that enhance convenience, they also pose significant social concerns. As defenders, current synthetic image detection methods often lack artifact-level textual interpretability and are…
Sequential Recommenders (SRs) are trained to predict the next item as the target given its preceding items as the input, assuming every input-target pair is matched and is reliable for training. However, users can be induced by external distractions to click on items inconsistent with their true pre…
Despite their remarkable performance on various tasks, Large Language Models (LLMs) still struggle with logical reasoning, particularly in complex and multi-step reasoning processes. Among various efforts to enhance LLMs' reasoning capabilities, synthesizing large-scale, high-quality logical reason…
Collective microrobots enable controlled batch delivery, showing promising application in the biomedical field. However, significant challenges remain in achieving long-distance delivery of collective microrobots in dynamic environments. This study proposes a magnetic actuation strategy for deliveri
Accurate segmentation of organs from abdominal CT scans is essential for clinical applications such as diagnosis, treatment planning, and patient monitoring. To handle challenges of heterogeneity in organ shapes, sizes, and complex anatomical relationships, we propose a Multi decoder network (MDNet)…
The rapid advancements in large language models (LLMs) have significantly enhanced natural language processing capabilities, facilitating the development of AudioLLMs that process and understand speech and audio inputs alongside text. Existing AudioLLMs typically combine a pre-trained audio encoder…
Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. In this paper, we systematically explore the abilities of open LLMs with less than ten billion parameters to handle multi…
Deep learning-based approaches have demonstrated significant advancements in time series forecasting. Despite these ongoing developments, the complex dynamics of time series make it challenging to establish the rule of thumb for designing the golden model architecture. In this study, we argue that r
Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without retraining. As an essential part of RAG, external knowledge bases are commonly built by extracting structured data from…
Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that such data aids multimodal in-context learning and maintains th…
Document content extraction is a critical task in computer vision, underpinning the data needs of large language models (LLMs) and retrieval-augmented generation (RAG) systems. Despite recent progress, current document parsing methods have not been fairly and comprehensively evaluated due to the nar…
Virtual Try-ON (VTON) is a practical and widely-applied task, for which most of existing works focus on clothes. This paper presents OmniTry, a unified framework that extends VTON beyond garment to encompass any wearable objects, e.g., jewelries and accessories, with mask-free setting for more pract…
Interactive segmentation aims to accurately segment target objects with minimal user interactions. However, current methods often fail to accurately separate target objects from the background, due to a limited understanding of order, the relative depth between objects in a scene. To address this is…
Low-rank adaptation (LoRA) and its variants have recently gained much interest due to their ability to avoid excessive inference costs. However, LoRA still encounters the following challenges: (1) Limitation of low-rank assumption; and (2) Its initialization method may be suboptimal. To this end, we…
Video object removal has achieved advanced performance due to the recent success of video generative models. However, when addressing the side effects of objects, \textit{e.g.,} their shadows and reflections, existing works struggle to eliminate these effects for the scarcity of paired video data as…
The scale and quality of datasets are crucial for training robust perception models. However, obtaining large-scale annotated data is both costly and time-consuming. Generative models have emerged as a powerful tool for data augmentation by synthesizing samples that adhere to desired distributions.…
Recently, mobile AI agents have gained increasing attention. Given a task, mobile AI agents can interact with mobile devices in multiple steps and finally form a GUI flow that solves the task. However, existing agents tend to focus on most task-relevant elements at each step, leading to local optima…
Security in code generation remains a pivotal challenge when applying large language models (LLMs). This paper introduces RefleXGen, an innovative method that significantly enhances code security by integrating Retrieval-Augmented Generation (RAG) techniques with guided self-reflection mechanisms in…
Video Moment Retrieval (VMR) aims to identify a temporal segment in an untrimmed video that best matches a given textual query. Bias in VMR is a critical issue, where the model achieves favorable results even if disregarding the video input. Existing evaluation methods, such as Resplitting, have att…
Recently, Mamba-based methods have gained popularity in medical image segmentation due to their ability to model long-range dependencies with linear computational complexity. However, current segmentation methods often face challenges such as low contrast, blurred boundaries, and unclear backgrounds…
Fine-tuning is a key approach for adapting language models to specific downstream tasks, but updating all model parameters becomes impractical as model sizes increase.Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), address this challenge by introducing additional…
Survey paper plays a crucial role in scientific research, especially given the rapid growth of research publications. Recently, researchers have begun using LLMs to automate survey generation for better efficiency. However, the quality gap between LLM-generated surveys and those written by human rem…
As the scale of vision models continues to grow, Visual Prompt Timing (VPT) has emerged as a parameter-efficient transfer learning technique, noted for its superior performance compared to full fine-tuning. However, indiscriminately applying prompts to every layer without considering their inherent…
Temporal awareness is essential for video large language models (LLMs) to understand and reason about events within long videos, enabling applications like dense video captioning and temporal video grounding in a unified system. However, the scarcity of long videos with detailed captions and precise…
Camouflaged Object Detection (COD) seeks to distinguish objects from their highly similar backgrounds. Existing work has essentially focused on isolating camouflaged objects from the environment, demonstrating ever-improving performance but at the cost of extensive annotations and complex optimizati…
Traffic prediction is critical for optimizing travel scheduling and enhancing public safety, yet the complex spatial and temporal dynamics within traffic data present significant challenges for accurate forecasting. In this paper, we introduce a novel model, the Spatiotemporal-aware Trend-Seasonalit…
Zeroth-order (ZO) optimization as the gradient-free method has become a powerful tool when the first-order gradient is unavailable or expensive to obtain, especially in decentralized learning scenarios where data and computational resources are distributed across multiple clients. There have been ma…
The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead. Existing works mitigate this burden by offloading or compressing the KV cache. However, loading the entire cache incurs significant latency due to PCIe bandwidth bottlenecks in CPU-GPU communi…
Large Language Models (LLMs), built on Transformer architectures, exhibit remarkable generalization across a wide range of tasks. However, fine-tuning these models for specific tasks remains resource-intensive due to their extensive parameterization. In this paper, we explore two remarkable phenomen
Function calling significantly extends the application boundary of large language models (LLMs), where high-quality and diverse training data is critical for unlocking this capability. However, collecting and annotating real function-calling data is challenging, while synthetic data from existing pi…
The paper targets the challenging task of Ship License Plate (SLP) recognition. Existing methods for SLP recognition are hampered by the scarcity of large and publicly available datasets, leading to evaluations on small and non-representative datasets. To alleviate it, we have built a large dataset,…
Automatic assembly of board-to-board (BTB) connectors remains a significant challenge in smartphone manufacturing due to severe visual occlusion, tight assembly tolerances, and process constraints that prohibit separate visual adjustment stations. This letter proposes Visual-Privileged Co-Learning (
Recent years, multi-hop reasoning has been widely studied for knowledge graph (KG) reasoning due to its efficacy and interpretability. However, previous multi-hop reasoning approaches are subject to two primary shortcomings. First, agents struggle to learn effective and robust policies at the early…
In multimodal human-computer interaction, generating co-speech gestures is crucial for enhancing interaction naturalness and user experience. However, achieving synchronized and natural gesture sequences remains a significant challenge due to the complexity of modeling temporal dependencies across d…
Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques, which reduce the bits needed for model weights or activations w…
In this work, we consider a multi-server federated learning (FL) framework, referred to as Confederated Learning (CFL), in order to accommodate a larger number of users. To reduce the communication overhead of the CFL system, we propose a linearly convergent stochastic gradient method. The proposed…
This letter proposes a novel bionic bird claw with a digit-locking mechanism inspired by a tendon-locking mechanism (TLM). First, the biological mechanisms of both the bird digit-locked TLM (tendon locking) and the leg automatic digit flexion mechanism (ADFM) (quick digit flexion) of birds are intro
This paper introduces CN-RMA a novel approach for 3D indoor object detection from multi-view images. We observe the key challenge as the ambiguity of image and 3D correspondence without explicit geometry to provide occlusion information. To address this issue CN-RMA leverages the synergy of 3D recon…
Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks. To enhance the capabilities of LLMs to emulate human reasoning, prior studies have focused on modeling reasoning steps using various thought structures like chains, trees, or graphs. However, LLM-ba…
Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during inference. While traditional pruning methods have been employed…
Stochastic bilevel optimization tackles challenges involving nested optimization structures. Its fast-growing scale nowadays necessitates efficient distributed algorithms. In conventional distributed bilevel methods, each worker must transmit full-dimensional stochastic gradients to the server every…
The scale and quality of a dataset significantly impact the performance of deep models. However, acquiring large-scale annotated datasets is both a costly and time-consuming endeavor. To address this challenge, dataset expansion technologies aim to automatically augment datasets, unlocking the full…
Domain generalization aims to train models on multiple source domains so that they can generalize well to unseen target domains. Among many domain generalization methods, Fourier-transformbased domain generalization methods have gained popularity primarily because they exploit the power of Fourier t…
New categories may be introduced over time, or existing categories may need to be reclassified. Class incremental learning (CIL) is employed for the gradual acquisition of knowledge about new categories while preserving information about previously learned ones in such dynamic environments. It might…
This paper introduces EmpathyEar, a pioneering open-source, avatar-based multimodal empathetic chatbot, to fill the gap in traditional text-only empathetic response generation (ERG) systems. Leveraging the advancements of a large language model, combined with multimodal encoders and generators, Empa…
Robotics agents often struggle to understand and follow the multi-modal prompts in complex manipulation scenes which are challenging to be sufficiently and accurately described by text alone. Moreover for long-horizon manipulation tasks the deviation from general instruction tends to accumulate if l…
Knowledge-based Visual Question Answering (KBVQA) is a challenging task, which aims to answer an image related question based on external knowledge. Most of the works describe the semantic distance using the actual Euclidean distance between two nodes, which leads to distortion in modeling knowledge…
In nested Named entity recognition (NER), entities are nested with each other, and thus requiring more data annotations to address. This leads to the development of few-shot nested NER, where the prevalence of pretrained language models with in-context learning (ICL) offers promising solutions. In t…
Despite advancements, fine-tuning Large Language Models (LLMs) remains costly due to the extensive parameter count and substantial data requirements for model generalization. Accessibility to computing resources remains a barrier for the open-source community. To address this challenge, we propose t…
The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution. Recent efforts have aimed to enhance the high-resolution understanding capabilities of LVLMs, ye…
Segmenting vein from leaf images is challenging because of the strong expansibility, high connectivity and irregular distribution of vein patterns. Although several recent attempts have been made to apply CNNs to leaf vein segmentation, they are weak to capture global contexts of lower-order veins a…
We consider the problem of maximizing the minimum user achievable rate for downlink massive MIMO multi-user systems. The max-min formulation promotes fairness such that all users enjoy a similar quality of wireless service. Nevertheless, solving the max-min beamforming problem is challenging due to…
The Sparsely-Activated Mixture-of-Experts (MoE) architecture has gained popularity for scaling large language models (LLMs) due to the sub-linearly increasing computational costs. Despite its success, most of the current structure designs face the challenge that the experts share the same size such…
With the remarkable advancements of large language models (LLMs), LLM-based agents have become a research hotspot in human-computer interaction.However, there is a scarcity of benchmarks available for LLM-based mobile agents.Benchmarking these agents generally faces three main challenges:(1) The ine…
Recently, mobile AI agents based on VLMs have been gaining increasing attention. These works typically utilize VLM as a foundation, fine-tuning it with instruction-based mobile datasets. However, these VLMs are typically pre-trained on general-domain data, which often results in a lack of fundamenta…
Inferring social relationships from human mobility data holds significant value in real-life spatio-temporal applications, which inspires the development of a series of graph-based methods for inferring social relationships. Despite their effectiveness, we argue that previous methods either rely sol…
Hallucination posed as a pervasive challenge of multi-modal large language models (MLLMs) has significantly impeded their real-world usage that demands precise judgment. Existing methods mitigate this issue with either training with specific designed data or inferencing with external knowledge from…
"Despite CLIP [?] being the foundation model in numerous vision-language applications, CLIP suffers from a severe text spotting bias. Such bias causes CLIP models to ‘Parrot’ the visual text embedded within images while disregarding the authentic visual semantics. We uncover that in the most popular…
We address the issue of physical implausibility in multi-view neural reconstruction. While implicit representations have gained popularity in multi-view 3D reconstruction, previous work struggles to yield physically plausible results, limiting their utility in domains requiring rigorous physical acc…
Structured pruning fundamentally reduces computational and memory overheads of large language models (LLMs) and offers a feasible solution for end-side LLM deployment. Structurally pruned models remain dense and high-precision, highly compatible with further tuning and compression. However, as the c…
In the field of information extraction (IE), tasks across a wide range of modalities and their combinations have been traditionally studied in isolation, leaving a gap in deeply recognizing and analyzing cross-modal information. To address this, this work for the first time introduces the concept of…
As the rapidly advancing domain of natural language processing (NLP), large language models (LLMs) have emerged as powerful tools for interpreting human commands and generating text across various tasks. Nonetheless, the resilience of LLMs to handle text containing inherent errors, stemming from hum…
Estimating robot pose and joint angles is significant in advanced robotics, enabling applications like robot collaboration and online hand-eye calibration. However, the introduction of unknown joint angles makes prediction more complex than simple robot pose estimation, due to its higher dimensional…
Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA, compromising…
Infrared and visible image fusion is an important multimodal image processing task that aims to enhance computer vision performance by effectively fusing infrared and visible images. Although in recent years, many deep learning-based methods for infrared and visible image fusion have emerged. Howeve…
We present SeaEval, a benchmark for multilingual foundation models. In addition to characterizing how these models understand and reason with natural language, we also investigate how well they comprehend cultural practices, nuances, and values. Alongside standard accuracy metrics, we investigate th…
Recently, tool-augmented LLMs have gained increasing attention. Given an instruction, tool-augmented LLMs can interact with various external tools in multiple rounds and provide a final answer. However, previous LLMs were trained on overly detailed instructions, which included API names or parameter…
Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address this challenge, previous studies have proposed retrieving suitable tools for the LLM bas…
Saliency-based representation visualization (SRV) ($e.g.$, Grad-CAM) is one of the most classical and widely adopted explainable artificial intelligence (XAI) methods for its simplicity and efficiency. It can be used to interpret deep neural networks by locating saliency areas contributing the most…
This paper studies close-loop task planning, which refers to the process of generating a sequence of skills (a plan) to accomplish a specific goal while adapting the plan based on real-time observations. Recently, prompting Large Language Models (LLMs) to generate actions iteratively has become a pr…
The integration of visual encoders and large language models (LLMs) has driven recent progress in multimodal large language models (MLLMs). However, the scarcity of high-quality instruction-tuning data for vision-language tasks remains a challenge. The current leading paradigm, such as LLaVA, relies…
Current weakly-supervised semantic segmentation (WSSS) techniques concentrate on enhancing class activation maps (CAMs) with image-level annotations. Yet, the emphasis on producing these pseudo-labels often overshadows the pivotal role of training the segmentation model itself. This paper underscore…
Previous works on emotion recognition in conversation (ERC) follow a two-step paradigm, which can be summarized as first producing context-independent features via fine-tuning pretrained language models (PLMs) and then analyzing contextual information and dialogue structure information among the ext…
Placement is a critical step in modern chip design, aiming to determine the positions of circuit modules on the chip canvas. Recent works have shown that reinforcement learning (RL) can improve human performance in chip placement. However, such an RL-based approach suffers from long training time an…
Geometric transformations including translation, rotation, and scaling are commonly used operations in image processing. Besides, some of them are successfully used in developing effective knowledge graph embedding (KGE). Inspired by the synergy, we propose a new KGE model by leveraging all three op…
In this work, we decouple the iterative bi-level offline RL (value estimation and policy extraction) from the offline training phase, forming a non-iterative bi-level paradigm and avoiding the iterative error propagation over two levels. Specifically, this non-iterative paradigm allows us to conduct…
Dialogue rewriting aims to transform multi-turn, context-dependent dialogues into well-formed, context-independent text for most NLP systems. Previous dialogue rewriting benchmarks and systems assume a fluent and informative utterance to rewrite. Unfortunately, dialogue utterances from real-world sy…
Recovering the shape and appearance of real-world objects from natural 2D images is a long-standing and challenging inverse rendering problem. In this paper, we introduce a novel hybrid differentiable rendering method to efficiently reconstruct the 3D geometry and reflectance of a scene from multi-v…
Embodied AI is a crucial frontier in robotics, capable of planning and executing action sequences for robots to accomplish long-horizon tasks in physical environments. In this work, we introduce EmbodiedGPT, an end-to-end multi-modal foundation model for embodied AI, empowering embodied agents with…
Conventional knowledge distillation(KD) approaches are commonly employed to compress neural machine translation(NMT) models. However, they only obtain one lightweight student each time. Consequently, we have to conduct KD multiple times when different students are required at the same time, which co…
Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value. However, current studies on TIT are confronted with two main bottlenecks: 1) this task lacks a publicly availabl…
Fine-grained leaf image retrieval (FGLIR) aims to search similar leaf images in subspecies level which involves very high interclass visual similarity and accordingly poses great challenges to leaf image description. In this study, we introduce a new concept, named fan-beam binarization difference p…
We study the problem of few-shot physically-aware articulated mesh generation. By observing an articulated object dataset containing only a few examples, we wish to learn a model that can generate diverse meshes with high visual fidelity and physical validity. Previous mesh generative models either…
Knowledge graph completion (KGC) aims to discover missing relationships between entities in knowledge graphs (KGs). Most prior KGC work focuses on learning embeddings for entities and relations through a simple score function. Yet, a higher-dimensional embedding space is usually required for a bette…
In-Image Machine Translation (IIMT) aims to convert images containing texts from one language to another. Traditional approaches for this task are cascade methods, which utilize optical character recognition (OCR) followed by neural machine translation (NMT) and text rendering. However, the cascade…
Conventional dialogue summarization methods directly generate summaries and do not consider user's specific interests. This poses challenges in cases where the users are more focused on particular topics or aspects. With the advancement of instruction-finetuned language models, we introduce instruct…
Recent studies on end-to-end speech translation(ST) have facilitated the exploration of multilingual end-to-end ST and end-to-end simultaneous ST. In this paper, we investigate end-to-end simultaneous speech translation in a one-to-many multilingual setting which is closer to applications in real sc…
Recent work shows that well-designed adversarial examples can fool deep neural networks (DNNs). Due to their transferability, adversarial examples can also attack target models without extra information, called black-box attacks. However, most existing ensemble attacks depend on numerous substitute…
The exploration problem is one of the main challenges in deep reinforcement learning (RL). Recent promising works tried to handle the problem with population-based methods, which collect samples with diverse behaviors derived from a population of different exploratory policies. Adaptive policy selec…
Reliable pseudo labels from unlabeled data play a key role in semi-supervised object detection (SSOD). However, the state-of-the-art SSOD methods all rely on pseudo labels with high confidence, which ignore valuable pseudo labels with lower confidence. Additionally, the insufficient excavation for u…
Recently, diffusion model shines as a promising backbone for the sequence modeling paradigm in offline reinforcement learning(RL). However, these works mostly lack the generalization ability across tasks with reward or dynamics change. To tackle this challenge, in this paper we propose a task-orient…
Morality in dialogue systems has raised great attention in research recently. A moral dialogue system aligned with users’ values could enhance conversation engagement and user connections. In this paper, we propose a framework, MoralDial to train and evaluate moral dialogue systems. In our framework…
Knowledge base question answering (KBQA) is a challenging task that aims to retrieve correct answers from large-scale knowledge bases. Existing attempts primarily focus on entity representation and final answer reasoning, which results in limited supervision for this task. Moreover, the relations, w…
Are Federated Learning (FL) systems free from backdoor poisoning with the arsenal of various defense strategies deployed? This is an intriguing problem with significant practical implications regarding the utility of FL services. Despite the recent flourish of poisoning-resilient FL methods, our stu…
Look-up table (LUT)-based methods have shown the great efficacy in single image super-resolution (SR) task. However, previous methods don't delve into the essential reason of restricted receptive field (RF) size in LUT, which is caused by the interaction of space and channel features in vanilla co…
Simultaneous machine translation (SimulMT) models start translation before the end of the source sentence, making the translation monotonically aligned with the source sentence. However, the general full-sentence translation test set is acquired by offline translation of the entire source sentence,…
Sequential recommender systems (SRSs) are typically trained to predict the next item as the target given its preceding (and succeeding) items as the input. Such a paradigm assumes that every input-target pair is reliable for training. However, users can be induced to click on items that are inconsis…
Universal Information Extraction (Universal IE) aims to solve different extraction tasks in a uniform text-to-structure generation manner. Such a generation procedure tends to struggle when there exist complex information structures to be extracted. Retrieving knowledge from external knowledge bases…
Recent advances in detecting arbitrary objects in the real world are trained and evaluated on object detection datasets with a relatively restricted vocabulary. To facilitate the development of more general visual object detection, we propose V3Det, a vast vocabulary visual detection dataset with pr…
Dialogue summarization is abstractive in nature, making it suffer from factual errors. The factual correctness of summaries has the highest priority before practical applications. Many efforts have been made to improve faithfulness in text summarization. However, there is a lack of systematic study…
Template-based 3D object tracking still lacks a high-precision benchmark of real scenes due to the difficulty of annotating the accurate 3D poses of real moving video objects without using markers. In this paper, we present a multi-view approach to estimate the accurate 3D poses of real moving objec…
Cross-modal hashing has attracted considerable attention for large-scale multimodal data. Recent supervised cross-modal hashing methods using multi-label networks utilize the semantics of multi-labels to enhance retrieval accuracy, where label hash codes are learned independently. However, all these…
Existing commonsense knowledge bases often organize tuples in an isolated manner, which is deficient for commonsense conversational models to plan the next steps. To fill the gap, we curate a large-scale multi-turn human-written conversation corpus, and create the first Chinese commonsense conversat…
Adapting to the changes in transition dynamics is essential in robotic applications. By learning a conditional policy with a compact context, context-aware meta-reinforcement learning provides a flexible way to adjust behavior according to dynamics changes. However, in real-world applications, the a…
"Filter pruning is one of the most effective methods to compress deep convolutional networks (CNNs). In this paper, as a key component in filter pruning, We first propose a feature discrimination based filter importance criterion, namely Receptive Field Criterion (RFC). It turns the maximum activati…
Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of the supervised counterparts in most downstream tasks. In thi…
"Neural Radiance Fields (NeRF) show remarkable ability to render novel views of a certain scene by learning an implicit volumetric representation with only posed RGB images. Despite its impressiveness and simplicity, NeRF usually converges to sub-optimal solutions with incorrect geometries given few…
Word and sentence embeddings are useful feature representations in natural language processing. However, intrinsic evaluation for embeddings lags far behind, and there has been no significant update since the past decade. Word and sentence similarity tasks have become the de facto evaluation method.…
Unsupervised cross-domain NER task aims to solve the issues when data in a new domain are fully-unlabeled. It leverages labeled data from source domain to predict entities in unlabeled target domain. Since training models on large domain corpus is time-consuming, in this paper, we consider an altern…
Applying existing methods to emotional support conversation—which provides valuable assistance to people who are in need—has two major limitations: (a) they generally employ a conversation-level emotion label, which is too coarse-grained to capture user’s instant mental state; (b) most of them focus…
We introduce Perceiving Stroke-Semantic Context (PerSec), a new approach to self-supervised representation learning tailored for Scene Text Recognition (STR) task. Considering scene text images carry both visual and semantic properties, we equip our PerSec with dual context perceivers which can cont…
"The vulnerability of DNNs severely limits the application of it in the security-sensitive domains. Most of the existing methods improve the robustness of models from weight optimization, such as adversarial training and regularization. However, the architecture is also a key factor to robustness, w…
Existing deep image dehazing methods usually depend on supervised learning with a large number of hazy-clean image pairs which are expensive or difficult to collect. Moreover, dehazing performance of the learned model may deteriorate significantly when the training hazy-clean image pairs are insuffi…
While self-training achieves state-of-the-art results in semi-supervised object detection (SSOD), it severely suffers from foreground-background and foreground-foreground imbalances in SSOD. In this paper, we propose an Adaptive Class-Rebalancing Self-Training (ACRST) with a novel memory module call…
As increasing numbers of autonomous vehicles (AVs) are being deployed, it is important to construct a multi-agent self-driving (MASD) system for navigating traffic flows of AVs. In an MASD system, AVs not only navigate themselves to pursue their own goals, but also interact with each other to preven…
As one of the challenging NLP tasks, designing math word problem (MWP) solvers has attracted increasing research attention for the past few years. In previous work, models designed by taking into account the properties of the binary tree structure of mathematical expressions at the output side have…
Semantic parsing is a mainstream method of knowledge base question answering task that first generates a set of logical forms according to question and knowledge base (KB), and then selects the most matching one to get answers. However, existing selection methods are usually based on word-level matc…
This paper describes our submission to ICASSP 2022 Multi-channel Multi-party Meeting Transcription (M2MeT) Challenge. For Track 1, we propose several approaches to make the clustering-based speaker diarization system enable to handle overlapped speech. Front-end dereverberation and the direction-of-…
Open Information Extraction (OpenIE) facilitates the open-domain discovery of textual facts. However, the prevailing solutions evaluate OpenIE models on in-domain test sets aside from the training corpus, which certainly violates the initial task principle of domain-independence. In this paper, we p…
Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples. They require the model to translate both the authentic source sentence and its adversarial counterpart into t…
Electrocardiography (ECG) is a conventional method in arrhythmia diagnosis. In this paper, we proposed a novel neural network model which treats typical heartbeat classification task as ‘Translation’ problem. By introducing Transformer structure into model, and adding heartbeat-aware attention mecha…
Most sequential recommender systems (SRSs) predict next-item as target for each user given its preceding items as input, assuming that each input is related to its target. However, users may unintentionally click on items that are inconsistent with their preference. We emp…
Recent deep learning based methods have achieved impressive performance on paraphrase identification (PI), a fundamental NLP task, judging whether two sentences are semantically equivalent or not. However, their success heavily relies on massive labeled samples, which are time-consuming and expensiv…
Targeting both computing and coding efficiencies, we propose in this work a novel hierarchical bit-wise differential coding scheme to compress point cloud attributes. The encoder firstly quantizes and organizes the points into an octree structure and, for each internal node, picks its attribute(s) f…
Cross-domain slot filling is a challenging task in spoken language understanding due to the differences in text genre across domains. In this paper, we attempt to solve this task by exploiting the syntactic structures of user utterances, because these syntactic structures are actually accessible and…
Code generation aims to automatically generate a piece of code given an input natural language utterance. Currently, among dominant models, it is treated as a sequence-to-tree task, where a decoder outputs a sequence of actions corresponding to the pre-order traversal of an Abstract Syntax Tree. How…
Open Information Extraction (OpenIE) aims to discover textual facts from a given sentence. In essence, the facts contained in plain text are unordered. However, the popular OpenIE systems usually output facts sequentially in the way of predicting the next fact conditioned on the previous decoded one…
Model-based reinforcement learning aims to improve the sample efficiency of policy learning by modeling the dynamics of the environment. Recently, the latent dynamics model is further developed to enable fast planning in a compact space. It summarizes the high-dimensional experiences of an agent, wh…
In this paper, we propose a robust neural machine translation (NMT) framework to deal with homophone errors. The framework consists of a homophone noise detector and a syllable-aware NMT model. The detector identifies potential homophone errors in a textual sentence and converts them into syllables…
Recent researches show that pre-trained models (PTMs) are beneficial to Chinese Word Segmentation (CWS). However, PTMs used in previous works usually adopt language modeling as pre-training tasks, lacking task-specific prior segmentation knowledge and ignoring the discrepancy between pre-training ta…
In multi-turn dialog, utterances do not always take the full form of sentences (Carbonell 1983), which naturally makes understanding the dialog context more difficult. However, it is essential to fully grasp the dialog context to generate a reasonable response. Hence, in this paper, we propose to im…
In this paper, a novel navigation learning method in continuous action space among crowds based on relational graph is proposed which can be directly deployed on differential-drive mobile robots without any change. More specifically, in order to increase generalization ability in crowd sizes, Graph…
A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias. While most existing works implicitly achieve this with video-specific pretext tasks (e.g., predicting clip orders, time arrows, and paces), we develop a method that…
This paper presents a simple unsupervised visual representation learning method with a pretext task of discriminating all images in a dataset using a parametric, instance-level classifier. The overall framework is a replica of a supervised classification model, where semantic classes (e.g., dog, bir…
Co-part segmentation is an important problem in computer vision for its rich applications. We propose an unsupervised learning approach for co-part segmentation from images. For the training stage, we leverage motion information embedded in videos and explicitly extract latent representations to seg…
Radon transform is a popular mathematical tool for shape analysis. However, it cannot handle affine deformation. Although its extended version, trace transform, allow us to construct affine invariants, they are less informative and computational expensive due to the loss of spatial relationship betw…
The lack of sufficient training data in many domains, poses a major challenge to the construction of domain-specific machine reading comprehension (MRC) models with satisfying performance. In this paper, we propose a novel iterative multi-source mutual knowledge transfer framework for MRC. As an ext…
While numerous approaches have been developed to embed graphs into either Euclidean or hyperbolic spaces, they do not fully utilize the information available in graphs, or lack the flexibility to model intrinsic complex graph geometry. To utilize the strength of both Euclidean and hyperbolic geometr…