178 accepted papers
The miniaturization of thermal sensors for mobile platforms inherently limits their spatial resolution and textural fidelity, leading to blurry and less informative images. Existing thermal super-resolution (SR) methods can be grouped into single-image and RGB-guided approaches: the former struggles
Recent advances in speech large language models (SLMs) have improved speech recognition and translation in general domains, but accurately generating domain-specific terms or neologisms remains challenging. To address this, we propose Attention2Probability: attention-driven terminology probability e…
Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to a quadratic increase in the number of vision tokens and sign
Sequential recommendation aims to predict the next item based on historical interactions. To further enhance the reasoning capability in sequential recommendation, LLMs are employed to predict the next item or generate semantic IDs for item representation, given LLMs
Recent self-supervised pre-training methods for object detection often rely on generic object proposals for localization and semantic feature learning for classification, but they yield limited improvements when applied to Detection Transformers (DETR) due to a lack of architectural alignment. Hence
Being able to simulate the outcomes of actions in varied environments will revolutionize the development of generalist agents at scale. However, modeling these world dynamics, especially for dexterous robotics tasks, poses significant challenges due to limited data coverage and scarce action labels.…
With the rapid progress of video generation, demand for customized video editing is surging, where subject swapping constitutes a key component yet remains under-explored. Prevailing swapping approaches either specialize in narrow domains—such as human-body animation or hand-object interaction—or re…
Human interaction is inherently multimodal and full-duplex: we listen while watching, speak while acting, and fluidly adapt to turn-taking and interruptions. Realizing these capabilities is essential for building models simulating humans. We present ELLSA (End-to-end Listen, Look, Speak and Act), wh…
As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories are often too context-specific to transfer, while tool-level reuse ignores the c…
Latent diffusion models have enabled high-quality video synthesis, yet their inference remains costly and time-consuming. As diffusion transformers become increasingly efficient, the latency bottleneck inevitably shifts to VAE decoders. To reduce their latency while maintaining quality, we propose a…
Offline Safe Reinforcement Learning (OSRL) aims to learn a policy that achieves high performance in sequential decision-making while satisfying safety constraints, using only pre-collected datasets. Recent works, inspired by the strong capabilities of Generative Models (GMs), reformulate decision-ma…
Existing contrastive multi-view clustering methods rely on a pre-defined cluster number, limiting their flexibility in real-world scenarios lacking prior knowledge. To address this, we propose GROK, a novel framework driven by a cluster decision agent for unknown-$K$ multi-view clustering. It pionee…
Implicit neural representations (INRs) have achieved remarkable success in image representation and compression, but they require substantial training time and memory. Meanwhile, recent 2D Gaussian Splatting (GS) methods (\textit{e.g.}, GaussianImage) offer promising alternatives through efficient p
Reinforcement learning (RL) has emerged as a powerful post-training paradigm for large language models (LLMs), yet its effectiveness varies significantly across base models. While incorporating a pre-RL supervised fine-tuning (SFT) phase can enhance RL training, key questions remain: how long should…
Large Reasoning Models (LRMs) achieve promising results on complex reasoning tasks but remain susceptible to hallucinations. Existing hallucination detection methods based on Large Language Models (LLMs) often focus solely on final answers, overlooking inconsistencies between the answer and reasonin
Event cameras offer high-temporal-resolution sensing that remains reliable under high-speed motion and challenging lighting, making them promising for localization from LiDAR point clouds in GPS-denied and visually degraded environments. However, aligning sparse, asynchronous events with dense LiDAR…
Video diffusion models (DMs) have enabled high-quality video synthesis, but their computation costs scale quadratically with sequence length due to the nature of self-attention. While linear attention offers a more efficient alternative, fully replacing quadratic attention demands costly pretraining
Context modeling is fundamental to LiDAR point cloud compression. Existing methods rely on computationally intensive 3D contexts, such as voxel and octree, which struggle to balance the compression efficiency and coding speed. In this work, we propose a neural LiDAR compressor based on 2D context mo…
Physically-based rendering (PBR) provides a principled standard for realistic material–lighting interactions in computer graphics. Despite recent advances in generating PBR textures, existing methods fail to address two fundamental challenges: 1) materials decomposition from image prompts under limi…
Stereo image compression (SIC) has become increasingly vital with its applications surging in fields such as 3D reconstruction and autonomous navigation. Previous methods leverage cross-attention to model inter-view redundancy and employ autoregressive entropy models to predict probability distribut
Mixture-of-Experts (MoE) Multimodal large language models (MLLMs) excel at vision-language tasks, but they suffer from high computational inefficiency. To reduce inference overhead, expert skipping methods have been proposed to deactivate redundant experts based on the current input tokens. However,
Augmented Reality (AR) and Multimodal Large Language Models (LLMs) are rapidly evolving, providing unprecedented capabilities for human-computer interaction. However, their integration introduces a new attack surface for Social Engineering (SE). In this paper, we systematically investigate the feasi
The advent of "OCR 2.0" and large-scale vision-language models (VLMs) has set new benchmarks in text recogni- tion. However, these unified architectures often come with significant computational demands, challenges in precise text localization within complex layouts, and a propen- sity for textual h
Generative sequence modeling faces a fundamental tension between the expressivity of Transformers and the efficiency of linear sequence models. Existing efficient architectures are theoretically bounded by shallow, single-step linear updates, while powerful iterative methods like Test-Time Training …
Peptide-based drug design targeting “undruggable” proteins remains one of the most critical challenges in modern drug discovery. Conventional peptide-discovery pipelines rely on low-throughput experimental screening, which is both time-consuming and prohibitively expensive. Moreover, existing comput
Structured images (e.g., charts and geometric diagrams) remain challenging for multimodal large language models (MLLMs), as perceptual slips can cascade into erroneous conclusions. Intermediate visual cues can steer reasoning; however, existing cue-based methods are constrained with low-fidelity ima…
Recent decomposition-based approaches have achieved significant success in Multi-Objective Combinatorial Optimization (MOCO). However,existing methods typically rely exclusively on node-centric representations, failing to capture the complementary representations provided by edge features for proble…
Video diffusion models (DMs) have enabled high-quality video synthesis. Yet, their substantial computational and memory demands pose serious challenges to real-world deployment, even on high-end GPUs. As a commonly adopted solution, quantization has proven notable success in reducing cost for image…
This paper studies a reconfigurable intelligent surface (RIS)-enhanced decoupled symbiotic radio (SR) system in which a primary transmitter delivers common data to multiple primary receivers (PRs), while a RIS-based backscatter device sends secondary data to a backscatter receiver (BRx). Unlike conv…
As a mainstream technique for 3D reconstruction, 3D Gaussian splatting (3DGS) has been applied in a wide range of applications and services. Recent studies have revealed critical vulnerabilities in this pipeline and introduced computation cost attacks that lead to malicious resource occupancies and
The Distribution Matching Distillation (DMD) has been successfully applied to text-to-image diffusion models such as Stable Diffusion (SD) 1.5. However, vanilla DMD suffers from convergence difficulties on large-scale flow-based text-to-image models, such as SD 3.5 and FLUX. In this paper, we first…
This paper does not introduce a novel method but instead establishes a straightforward, incremental, yet essential baseline for video temporal grounding (VTG), a core capability in video understanding. While multimodal large language models (MLLMs) excel at various video understanding tasks, the rec
Fine-tuning large language models (LLMs) on custom datasets has become a standard approach for adapting these models to specific domains and applications. However, recent studies have shown that such fine-tuning can lead to significant degradation in the model's safety. Existing defense methods oper…
Large reasoning models (LRMs) achieve remarkable reasoning performance by generating long chains-of-thought (CoT). However, standard supervised fine-tuning (SFT) treats all tokens uniformly, indiscriminately minimizing loss across both essential reasoning steps and those that are noisy, redundant, o…
Inter-agent communication serves as an effective mechanism for enhancing performance in collaborative multi-agent reinforcement learning (MARL) systems. However, the inherent communication latency in practical systems induces both action decision delays and outdated information sharing, impeding MAR
This paper tackles \textbf{open-ended deep research (OEDR)}, a complex challenge where AI agents must synthesize vast web-scale information into insightful reports. Current approaches are plagued by dual-fold limitations: static research pipelines that decouple planning from evidence acquisition and…
Reasoning distillation, a cost-effective approach for enhancing student model performance, has attracted increasing attention. It typically leverages a large teacher model to generate reasoning paths, which are then used to fine-tune a student model so that it mimics the teacher's behavior in traini…
This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. WorldPlay draws power from three key innovations. 1) We use a Dual A…
World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training, making it challenging to adapt to novel environments with hetero…
Recent research showcases the considerable potential of conditional diffusion models for generating consistent stories. However, current methods, which primarily generate stories in a caption-dependent manner, often overlook the importance of contextual consistency and the relevance of frames durin…
Safe offline reinforcement learning aims to develop policies that maximize cumulative rewards while satisfying safety constraints without the need for risky online interaction. However, existing methods often struggle with the out-of-distribution (OOD) problem, leading to potentially unsafe and subo…
Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the spatial-disparity characteristics inherent in stereo images, w…
Speculative decoding has become a widely adopted as an effective technique for lossless inference acceleration when deploying large language models (LLMs). While on-the-fly self-speculative methods offer seamless integration and broad utility, they often fall short of the speed gains achieved by met…
Visual Place Recognition (VPR) is crucial for autonomous vehicles, as it enables their identification of previously visited locations. Compared with conventional single-frame retrieval, leveraging sequences of frames to depict places has been proven effective in alleviating perceptual aliasing. Howe
Code generation models have shown significant potential for programming tasks. However, existing training methods like supervised fine-tuning face key limitations: they do not effectively teach models to prioritize correct over incorrect solutions in ambiguous situations, nor do they effectively opt…
Multi-hop complex reasoning over incomplete knowledge graphs (KGs) has been extensively studied, but research on numerical knowledge graphs (NKGs) remains relatively limited. Recent approaches focus on separately encoding entities and numerical values, using neural networks to process query encoding
Continuum robots (CRs) possess better compliance than rigid manipulators. However, existing CRs suffer from difficulties in manipulating objects for the conflicting needs of high stiffness and flexibility. This letter proposes an elephant trunk-inspired CR for grasping and moving objects. The CR fea
In this paper, we introduce DimensionX, a framework designed to generate photorealistic 3D and 4D scenes from just a single image with video diffusion. Our approach begins with the insight that both the spatial structure of a 3D scene and the temporal evolution of a 4D scene can be effectively repre…
Large language models (LLMs) have achieved significant advances but can potentially generate harmful content such as social biases, extremism, and misinformation. Red teaming is a promising approach to enhance model safety by creating adversarial prompts to test and improve model robustness. However…
The quality of endoscopic images is critical to the success of polyp segmentation, highlighting the need for accurate exposure correction in endoscopy. While traditional deep learning methods are effective, they demand substantial computational resources during inference. To address this, we propose…
Event cameras are bio-inspired sensors with some notable features, including high dynamic range and low latency, which makes them exceptionally suitable for perception in challenging scenarios such as high-speed motion and extreme lighting conditions. In this paper, we explore their potential for lo
Speech quality assessment typically requires evaluating audio from multiple aspects, such as mean opinion score (MOS) and speaker similarity (SIM) etc., which can be challenging to cover using one small model designed for a single task. In this paper, we propose leveraging recently introduced audito…
The success of the text-guided diffusion model has inspired the development and release of numerous powerful diffusion models within the open-source community. These models are typically fine-tuned on various expert datasets, showcasing diverse denoising capabilities. Leveraging multiple high-qualit…
In cooperative multi-agent reinforcement learning (MARL), well-designed communication protocols can effectively facilitate consensus among agents, thereby enhancing task performance. Moreover, in large-scale multi-agent systems commonly found in real-world applications, effective communication plays…
The high-quality, realistic images generated by generative models pose significant challenges for exposing them. So far, data-driven deep neural networks have been justified as the most efficient forensics tools for the challenges. However, they may be over-fitted to certain semantics, resulting in…
We present FinMMR, a novel bilingual multimodal benchmark tailored to evaluate the reasoning capabilities of multimodal large language models (MLLMs) in financial numerical reasoning tasks. Compared to existing benchmarks, our work introduces three significant advancements. (1) Multimodality: We met…
With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters to CPU memory and loading activated experts on demand has emerged as a potential solution, the large size of activated…
Despite the remarkable successes of general-purpose neural networks, such as MLPs and Transformers, we find that they exhibit notable shortcomings in modeling and reasoning about periodic phenomena, achieving only marginal performance within the training domain and failing to generalize effectively…
We present GI-GS, a novel inverse rendering framework that leverages 3D Gaussian Splatting (3DGS) and deferred shading to achieve photo-realistic novel view synthesis and relighting. In inverse rendering, accurately modeling the shading processes of objects is essential for achieving high-fidelity r…
Retrieval augmented generation has revolutionized large language model (LLM) outputs by providing factual supports. Nevertheless, it struggles to capture all the necessary knowledge for complex reasoning questions. Existing retrieval methods typically divide reference documents into passages, treati…
Feature selection can increase the classification accuracy and reduce the scale of feature subset, which is important in various machine learning tasks. However, there are various preferences and limitations for the usage of features in different application scenes, and thus different scenes may req…
Diffusion Transformers (DiTs) excel in generative tasks but face practical deployment challenges due to high inference costs. Feature caching, which stores and retrieves redundant computations, offers the potential for acceleration. Existing learning-based caching, though adaptive, overlooks the imp…
Various research has addressed the overconfidence problem, and we focus on improving the robustness of post-hoc calibration (e.g., temperature scaling, TS) when the test set shifts from the training set by image corruption. TS is greatly affected by the validation set, which previous work has propos…
Spoken language understanding (SLU) is a structure prediction task in the field of speech. Recently, many works on SLU that treat it as a sequence-to-sequence task have achieved great success. However, This method is not suitable for simultaneous speech recognition and understanding. In this paper,…
Accurate Six Degrees of Freedom (6-DoF) pose estimation of Ship-To-Shore (STS) quay crane spreaders is crucial for ensuring safe and efficient container handling in port automation. However, existing pose estimation techniques face significant challenges, as camera-based systems either rely on marke
Federated learning (FL) enables collaborative learning among decentralized clients while safeguarding the privacy of their local data. Existing studies on FL typically assume offline labeled data available at each client when the training starts. Nevertheless, the training data in practice often arr…
In this work, we investigate a typical scenario in code generation where a developer edits existing code in real time and requests a code assistant, e.g., a large language model, to re-predict the next token or next line on the fly. Naively, the LLM needs to re-encode the entire KV cache to provide…
Reasoning models have demonstrated remarkable performance on complex tasks by generating long reasoning traces prior to producing final answers. However, previous research on long-context scaling in language models has generally focused on managing lengthy input prompts instead of producing long out
4D Gaussian Splatting (4DGS) has recently emerged as a promising technique for capturing complex dynamic 3D scenes with high fidelity. It utilizes a 4D Gaussian representation and a GPU-friendly rasterizer, enabling rapid rendering speeds. Despite its advantages, 4DGS faces significant challenges, n…
Birds can generate sufficient lift and save energy by folding their wings. Inspired by this, we design a flapping-wing robot featuring passively foldable wings with compliant joints. The joints comprise a flexible beam and blocks, enabling asymmetric wing folding motions. The wings are modeled as th
External ocean disturbances (EODs) and internal thruster loss-of-effectiveness faults (ITLEFs) are key factors influencing the accuracy of the autonomous tugboat's path following, as well as the stability and safety of the tugboat's hull during maritime operations. To achieve robust path following f
Accurate Relative Pose Estimation (RPE) is critical for effective collaboration of multi-robot systems. Traditional methods using cameras or LiDARs heavily rely on overlapping Fields of View (FoV) between robots, which is highly demanding in practical applications and may hinder collaboration effici
This paper explores a novel perspective to speech quality assessment by leveraging natural language descriptions, offering richer, more nuanced insights than traditional numerical scoring methods. Natural language feedback provides instructive recommendations and detailed evaluations, yet existing d…
Reinforcement learning (RL) has proven to be well-performed and versatile in inventory control (IC). However, further improvement of RL algorithms in the IC domain is impeded by two limitations of online experience. First, online experience is expensive to acquire in real-world applications. With th…
In order to enable fluid and natural human-machine speech interaction, existing full-duplex conversational systems often adopt modular architectures with auxiliary components such as voice activity detectors, interrupters, conversation state predictors, or multiple LLMs. These systems, however, suff…
Spatio-temporal trajectory representation learning plays a crucial role in various urban applications such as transportation systems, urban planning, and environmental monitoring. Existing methods can be divided into single-view and multi-view approaches, with the latter offering richer representati…
Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality. It works by first employing a compact model to draft multiple tokens efficiently and then using the target LLM to verify them in parallel. While this technique has achieved notab…
Large language models (LLMs) have achieved groundbreaking progress in Natural Language Processing (NLP). Despite the numerous advantages of LLMs, they also pose significant safety risks. Self-evaluation mechanisms have gained increasing attention as a key safeguard to ensure safe and controllable co
Scene Graph Generation (SGG) aims to detect all objects and identify their pairwise relationships existing in the scene. Considering the substantial human labor costs, existing scene graph annotations are often sparse and biased, which result in confusion training with low-frequency predicates. In t…
Video large language models (Vid-LLMs) have shown strong capabilities in understanding video content. However, their reliance on dense video token representations introduces substantial memory and computational overhead in both prefilling and decoding. To mitigate the information loss of recent vide
Consider an integrated sensing and communication (ISAC) system where a base station (BS) employs a full-duplex radio to simultaneously serve multiple users and detect a target. The detection performance of the BS may be compromised by self-interference (SI) leakage. This paper investigates the feasi…
Large Language Models (LLMs) have significantly advanced natural language processing with exceptional task generalization capabilities. Low-Rank Adaption (LoRA) offers a cost-effective fine-tuning solution, freezing the original model parameters and training only lightweight, low-rank adapter matric…
The Self-Reconfiguring Flight Structure (SRFS), consisting of quadrotor Unmanned Aerial Vehicle (UAV) units, is more functional, but still in its infancy because docking efficiency and security are hardly guaranteed. To obtain SRFS by docking, it is important to generate a safe and efficient traject
Advancements in distributed training and efficient attention mechanisms have significantly expanded the context window sizes of large language models (LLMs). However, recent work reveals that the effective context lengths of open-source LLMs often fall short, typically not exceeding half of their tr…
Despite the remarkable performance of multimodal large language models (MLLMs) across diverse tasks, the substantial training and inference costs impede their advancement. In this paper, we propose p-MoD, an efficient MLLM architecture that significantly reduces training and inference costs while ma…
Large language models (LLMs) have achieved impressive advancements across numerous disciplines, yet the critical issue of knowledge conflicts, a major source of hallucinations, has rarely been studied. While a few research explored the conflicts between the inherent knowledge of LLMs and the retriev…
Recent work has showcased the significant potential of diffusion models in pose-guided person image synthesis. However, owing to the inconsistency in pose between the source and target images, synthesizing an image with a distinct pose, relying exclusively on the source image and target pose informa…
Time-varying graphical LASSO (TVGL) aims to infer a sequence of graphs from time series data and has been widely used in many statistical inference problems. The existing algorithms usually suffer from high computational cost when solving large-scale TVGL problems. In this paper, we develop an effic…
Autonomous takeoff of flapping-wing robots (FWRs) is crucial for accelerating response speed and reducing costs in executing tasks. Jumping-aided takeoff is an effective method adopted by birds. However, the limited power density of motors poses challenges in achieving this type of takeoff for FWRs.…
The lack of object-level labels presents a significant challenge for 3D object retrieval in the open-set environment. However, part-level shapes of objects often share commonalities across categories but remain underexploited in existing retrieval methods. In this paper, we introduce the Hypergraph-…
Deep learning has shown promising results for multiple 3D point cloud registration datasets. However, in the underwater domain, most registration of multibeam echo-sounder (MBES) point cloud data are still performed using classical methods in the iterative closest point (ICP) family. In this work, w…
"With the rapid advancement of stereo vision technologies, stereo image compression has emerged as a crucial field that continues to draw significant attention. Previous approaches have primarily employed a unidirectional paradigm, where the compression of one view is dependent on the other, resulti…
Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing showing remarkable versatility across various video tasks. However existing methods often fail to fully leverage their representation capabilities primarily due to inadequate alignment of int…
Unlike general text summarization, Query-focused summarization (QFS) is severely limited by insufficient datasets, forcing previous research to transform datasets from other tasks into QFS format for data augmentation. However, this approach has resulted in two problems: the task and traintest gaps.…
In order to control the inter-cell interference for a multi-cell multi-user multiple-input multiple-output network, we consider the precoder design for coordinated multi-point with downlink coherent joint transmission. To avoid costly information exchange among the cooperating base stations in a cen…
We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The drafting stage generates draft tokens at a slightly lower quali…
In this paper we introduce the first large-scale video prediction model in the autonomous driving discipline. To eliminate the restriction of high-cost data collection and empower the generalization ability of our model we acquire massive data from the web and pair it with diverse and high-quality t…
In multi-agent reinforcement learning (MARL), effective exploration is critical, especially in sparse reward environments. Although introducing global intrinsic rewards can foster exploration in such settings, it often complicates credit assignment among agents. To address this difficulty, we propos…
In multi-agent reinforcement learning (MARL), parameter sharing is commonly employed to enhance sample efficiency. However, the popular approach of full parameter sharing often leads to homogeneous policies among agents, potentially limiting the performance benefits that could be derived from policy…
Recently, there has been growing interest in long-context scaling of large language models (LLMs). To facilitate research in this field, we propose L-Eval to institute a more standardized evaluation for Long-Context Language Models (LCLMs) addressing two key aspects: dataset construction and evaluat…
As a new sensor, 4D radar (x, y, z, velocity) has great potential for V2X, due to its 3D point cloud, direct doppler velocity output, long distance ranging, low-cost, and more importantly, robust perception in all weathers. However, the extrinsic calibration of multiple long baseline 4D radars is ra…
Temporal reasoning is fundamental for large language models (LLMs) to comprehend the world. Current temporal reasoning datasets are limited to questions about single or isolated events, falling short in mirroring the realistic temporal characteristics involving concurrent nature and intricate tempor…
Multi-session mapping serves as the pre-requisite for autonomous robots to fulfill various long-term tasks (e.g., map updating, navigation, collaboration). However, it is challenging to implement multi-session mapping in enclosed or partially enclosed ambiguous environments (e.g., long corridors, in…
Twisted string actuators (TSA) exhibit desirable traits for robotic applications like enabling high-force actuation. It is important to understand TSAs' key performance metrics to allow for ubiquitous usage. However, performance analysis of TSAs is challenging due to the strong coupling between the
Adversarial examples are commonly created by solving a constrained optimization problem, typically using sign-based methods like Fast Gradient Sign Method (FGSM). These attacks can benefit from momentum with a constant parameter, such as Momentum Iterative FGSM (MI-FGSM), to enhance black-box transf…
Multi-talker automatic speech recognition plays a crucial role in scenarios involving multi-party interactions, such as meetings and conversations. Due to its inherent complexity, this task has been receiving increasing attention. Notably, the serialized output training (SOT) stands out among variou…
Speech encompasses a wealth of information, including but not limited to content, paralinguistic, and environmental information. This comprehensive nature of speech significantly impacts communication and is crucial for human-computer interaction. Chat-Oriented Large Language Models (LLMs), known fo…
Existing open-set learning methods consider only the single-layer labels of objects and strictly assume no overlap between the training and testing sets, leading to contradictory optimization for superposed categories. In this paper, we introduce a more practical Semi-Open Environment setting for op…
Prior research on deep video compression (DVC) for machine tasks typically necessitates training a unique codec for each specific task mandating a dedicated decoder per task. In contrast traditional video codecs employ a flexible encoder controller enabling the adaptation of a single codec to differ…
The ability of Large Language Models (LLMs) to process and generate coherent text is markedly weakened when the number of input tokens exceeds their pretraining length. Given the expensive overhead of finetuning large-scale models with longer sequences, we propose a training-free approach named Dual…
Place Recognition is crucial for unmanned vehicles in terms of localization and mapping. Recent years have witnessed numerous explorations in the field where 2D cameras and 3D LiDARs are mostly employed. Despite their admirable performance they may encounter challenges in adverse weather such as rai…
Creating stable, controllable videos is a complex task due to the need for significant variation in temporal dynamics and cross-frame temporal consistency. To address this, we enhance the spatial-temporal capability and introduce a versatile video generation model, VersVideo, which leverages textual…
World models can foresee the outcomes of different actions, which is of paramount importance for autonomous driving. Nevertheless, existing driving world models still have limitations in generalization to unseen environments, prediction fidelity of critical details, and action controllability for fl…
LiDAR-based SLAM may easily fail in adverse weathers (e.g., rain, snow, smoke, fog), while mmWave Radar remains unaffected. However, current researches are primarily focused on 2D (x,y)(x,y) or 3D (x, yx, y, doppler) Radar and 3D LiDAR, while limited work can be found for 4D Radar (x, y, zx, y, z, d…
Visual Place Recognition (VPR) is essential for autonomous robots and unmanned vehicles, as an accurate identification of visited places can trigger a loop closure to optimize the built map. The most prevalent methods tackle VPR as a single-frame retrieval task, which uses a CNN-based encoder to des…
Transformer has achieved remarkable success in language, image, and speech processing. Recently, various efficient attention architectures have been proposed to improve transformer's efficiency while largely preserving its efficacy, especially in modeling long sequences. A widely-used benchmark to t…
Robust visual place recognition (VPR) against significant appearance changes is crucial for the life-long operation of mobile robots. Focusing on this task, we propose a Co-Attentive Hierarchical Image Representations (CAHIR) framework for VPR, which unifies attention-sharing global and local descri…
Speech or text representation generated by pre-trained models contains modal-specific information that could be combined for benefiting spoken language understanding (SLU) tasks. In this work, we propose a novel pre-training paradigm termed Continuous Integrate-and-Fire Pre-Training (CIF-PT). It rel…
The classification of gigapixel-sized whole slide images (WSIs) with slide-level labels can be formulated as a multiple-instance-learning (MIL) problem. State-of-the-art models often consist of two decoupled parts: local feature embedding with a pre-trained model followed by a global feature aggrega…
Compared with previous two-stream trackers, the recent one-stream tracking pipeline, which allows earlier interaction between the template and search region, has achieved a remarkable performance gain. However, existing one-stream trackers always let the template interact with all parts inside the s…
Accurate global localization is an essential ingredient for autonomous mobile robots (AMRs) operating in enclosed or partially enclosed repetitive environments (e.g., office corridors, industrial warehouses, transportation centers). In such environments, the Global Navigation Satellite System (GNSS)…
Most biomedical pretrained language models are monolingual and cannot handle the growing cross-lingual requirements. The scarcity of non-English domain corpora, not to mention parallel data, poses a significant hurdle in training multilingual biomedical models. Since knowledge forms the core of doma…
In V2X (Vehicle-to-Everything), one important work is to extrinsically calibrate multiple 3D LiDARs, which are mounted with a long baseline and large viewpoint-difference at the road-side. Current solutions either require a specific target being set up (e.g., a sphere), or require specific features…
Multi-view image compression plays a critical role in 3D-related applications. Existing methods adopt a predictive coding architecture, which requires joint encoding to compress the corresponding disparity as well as residual information. This demands collaboration among cameras and enforces the epi…
Camouflaged Object Detection (COD) aims to segment objects that blend in with their surroundings. Most existing methods mainly tackle this issue by a single-stage framework, which tends to degrade performance in the face of small objects, low-contrast objects and objects with diverse appearances. In…
Deep learning video compression outperforms its hand-craft counterparts with enhanced flexibility and capacity. One key component of the learned video codec is the autoregressive entropy model conditioned on spatial and temporal priors. Operating autoregressive on raster scanning order naively treat…
Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic relevance and data inefficiency for each area in the slide. Most of the existing methods rely on a multiple instance learnin…
Human visual perception can easily generalize to out-of-distributed visual data, which is far beyond the capability of modern machine learning models. Domain generalization (DG) aims to close this gap, with existing DG methods mainly focusing on the loss function design. In this paper, we propose to…
This paper focuses on improving the calibration performance of the post-hoc approach for the distributional shift. Taking the popular temperature scaling (TS) as a case in point, the key task is finding a matched temperature for the shifted test set. To address this issue, we pose an insight that te…
Recent work has demonstrated that pretrained transformers are overconfident in text classification tasks, which can be calibrated by the famous post-hoc calibration method temperature scaling (TS). Character or word spelling mistakes are frequently encountered in real applications and greatly threat…
Last-mile delivery robots are usually required to navigate on the sidewalk through a fixed route. The current solutions heavily rely on the image-based perception and GPS localization to successfully complete delivery tasks. However, it is prone to fail and become unreliable when the robot runs in c…
Federated learning (FL) strives to enable collaborative training of machine learning models without centrally collecting clients' private data. Different from centralized training, the local datasets across clients in FL are non-independent and identically distributed (non-IID). In addition, the dat…
Multi-LiDAR system is an important part of V2X (Vehicle to Everything) to enhance the perception information for unmanned vehicles. To fuse the information from multiple 3D LiDARs, accurate extrinsic calibration between the LiDARs is essential. However, the existing multi-LiDAR calibration methods m…
We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. We build our method on Transformers for its efficacy. Although we have witnessed great progress for video action recognition in the past decade, it remains challenging yet valu…
The large-scale whole-slide images (WSIs) facilitate the learning-based computational pathology methods. However, the gigapixel size of WSIs makes it hard to train a conventional model directly. Current approaches typically adopt multiple-instance learning (MIL) to tackle this problem. Among them, M…
Place recognition is an important capability for autonomously navigating vehicles operating in complex environments and under changing conditions. It is a key component for tasks such as loop closing in SLAM or global localization. In this letter, we address the problem of place recognition based on
Large-scale vision-language pre-training has achieved promising results on downstream tasks. Existing methods highly rely on the assumption that the image-text pairs crawled from the Internet are in perfect one-to-one correspondence. However, in real scenarios, this assumption can be difficult to ho…
Weakly-supervised whole-slide image (WSI) classification (WSWC) is a challenging task where a large number of unlabeled patches (instances) exist within each WSI (bag) while only a slide label is given. Despite recent progress for the multiple instance learning (MIL)-based WSI analysis, the major l…
Place recognition is seen as a crucial factor to correct cumulative errors in Simultaneous Localization and Mapping (SLAM) applications. Most existing studies focus on visual place recognition, which is inherently sensitive to environmental changes such as illumination, weather and seasons. Consider…
Cross-modal retrieval between videos and texts has gained increasing interest because of the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part of the information. Thus, a video can have multiple different…
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-…
The presence of haze significantly reduces the quality of images. Researchers have designed a variety of algorithms for image dehazing (ID) to restore the quality of hazy images. However, there are few studies that summarize the deep learning (DL) based dehazing technologies. In this paper, we condu…
Text-based image retrieval has seen considerable progress in recent years. However, the performance of existing methods suffers in real life since the user is likely to provide an incomplete description of an image, which often leads to results filled with false positives that fit the incomplete des…
The core of visual place recognition (VPR) lies in how to identify task-relevant visual cues and embed them into discriminative representations. Focusing on these two points, we propose a novel encoding strategy named Attentional Pyramid Pooling of Salient Visual Residuals (APPSVR). It incorporates…
The recent advancements of three-dimensional (3D) data acquisition devices have spurred a new breed of applications that rely on point cloud data processing. However, processing a large volume of point cloud data brings a significant workload on resource-constrained mobile devices, prohibiting from…
The immunohistochemistry (IHC) test of biopsy tissue is crucial to develop targeted treatment and evaluate prognosis for cancer patients. The IHC staining slide is usually digitized into the whole-slide image (WSI) with gigapixels for quantitative image analysis. To perform a whole image prediction…
Twisted string actuators (TSAs) have exhibited great promise in robotic applications by generating high translational force with low input torque. Despite great success, it remains a challenge to reliably estimate the strain of TSAs using compact solutions while maintaining actuator compliance. The
User modeling is critical for developing personalized services in industry. A common way for user modeling is to learn user representations that can be distinguished by their interests or preferences. In this work, we focus on developing universal user representation model. The obtained universal re…
Recommendation dialogs require the system to build a social bond with users to gain trust and develop affinity in order to increase the chance of a successful recommendation. It is beneficial to divide up, such conversations with multiple subgoals (such as social chat, question answering, recommenda…
It is well acknowledged that person re-identification (person ReID) highly relies on visual texture information like clothing. Despite significant progress has been made in recent years, texture-confusing situations like clothing changing and persons wearing the same clothes receive little attention…
Symmetric environment is one of the most intractable and challenging scenarios for mobile robots to accomplish global localization tasks, due to the highly similar geometrical structures and insufficient distinctive features. Existing localization solutions in such scenarios either depend on pre-dep…
Nucleus instance segmentation and classification in histopathological images is an essential prerequisite in pathology diagnosis/prognosis. However, nucleus annotations (e.g., segmentation and labeling) require domain experts, and annotating nuclei at pixel-level is time-consuming and labor-intensiv…
Large-scale visual place recognition (VPR) is inherently challenging because not all visual cues in the image are beneficial to the task. In order to highlight the task-relevant visual cues in the feature embedding, the existing attention mechanisms are either based on artificial rules or trained in…
Out-of-Distribution (OOD) detection is an important problem in natural language processing (NLP). In this work, we propose a simple yet effective framework kFolden, which mimics the behaviors of OOD detection during training without the use of any external data. For a task with k training labels, kF…
Performing collaborative semantic mapping is a critical challenge for cooperative robots to maintain a comprehensive contextual understanding of the surroundings. Most of the existing work either focus on single robot semantic mapping or collaborative geometry mapping. In this paper, a novel hierarc…
This paper considers the grant-free random access scheme in IoT networks with a massive number of devices. By embedding the data symbols in the signature sequences, joint device activity detection, and data decoding can be achieved, which, however, significantly increases the computational complexit…
Dictionary learning is a classic representation learning method that has been widely applied in signal processing and data analytics. In this paper, we investigate a family of $\ell_p$-norm ($p>2,p \in N$) maximization approaches for the complete dictionary learning problem from theoretical and algo…
Enabling long-term operation during day and night for collaborative robots requires a comprehensive understanding of the unstructured environment. Besides, in the dynamic environment, robots must be able to recognize dynamic objects and collaboratively build a global map. This paper proposes a novel…
The nature-inspired behavior of collective motion is found to be an optimal solution in swarming systems for predator avoidance and survival. In this work, we propose a two-level control architecture for multi-robot systems (MRS), which leverages the advantages of flocking control and function appro
In the conventional person Re-ID setting, it is assumed that cropped images are the person images within the bounding box for each individual. However, in a crowded scene, off-shelf-detectors may generate bounding boxes involving multiple people, where the large proportion of background pedestrians…
The static world assumption is standard in most simultaneous localisation and mapping (SLAM) algorithms. Increased deployment of autonomous systems to unstructured dynamic environments is driving a need to identify moving objects and estimate their velocity in real-time. Most existing SLAM based app…
We propose a self-supervised Gaussian ATtention network for image Clustering (GATCluster). Rather than extracting intermediate features first and then performing traditional clustering algorithms, GATCluster directly outputs semantic cluster labels without further post-processing. We give a Label Fe…
Supercoiled polymer (SCP) artificial muscles exhibit many desirable properties such as large contractions and high power density. However, their full potential as robotic muscles is challenged by insufficient strain or force generation – non-mandrel-coiled SCP actuators produce up to 10-20% strain;…
As a recently developed artificial muscle, supercoiled polymer (SCP) actuators exhibit many desirable properties such as inherent compliance, large linear tensile actuation, and high energy and power densities. By embedding linear SCP actuators into flexible beams and activating them, bending SCP ac
Multiple instance learning (MIL) is a typical weakly-supervised learning method where the label is associated with a bag of instances instead of a single instance. Despite extensive research over past years, effectively deploying MIL remains an open and challenging problem, especially when the commo…
Human-multi-robot collaboration is becoming more and more common in intelligent manufacturing. Optimal assembly scheduling of such systems plays a critical role in their production efficiency. Existing approaches mostly consider humans as agents with assumed or known capabilities, which leads to sub…
The problem of tracking self-motion as well as motion of objects in the scene using information from a camera is known as multi-body visual odometry and is a challenging task. This paper proposes a robust solution to achieve accurate estimation and consistent track-ability for dynamic multi-body vis…
Video saliency should be taken into consideration to facilitate optimization of the end-to-end video production, delivery and consumption ecosystem to improve user experience at lowered cost. Although recent studies have significantly increased the accuracy of saliency prediction, the approaches are…
It is strongly desirable but challenging to obtain force sensing mechanisms that are low-cost, volumetrically compact, away from contact location, and can be easily integrated into existing and emerging robot systems. For example, having a bulky force sensor near the tip of surgical robot tools may
Successful sampling on the surface of asteroids is difficult because of their weightless environment and unknown material mechanical property. This work presents an asteroid sampler based on sweeping and grinding methods to improve the success rate of sampling. The sampler uses two brushes rotating…
Maximum entropy language models (MaxEnt LMs) are log-linear models which are able to incorporate various hand-crafted features and non-linguistic information. Standard MaxEnt LMs are computationally heavy for tasks with a large vocabulary size due to the expensive normalization computation in the de…
Super-coiled polymer (SCP) artificial muscles have many attractive properties, such as high energy density, large contractions, and good dynamic range. To fully utilize them for robotic applications, it is necessary to determine how to scale them up effectively. Bundling of SCP actuators, as though
The supercoiled polymer (SCP) actuator is a recently discovered artificial muscle that demonstrates significant mechanical power, large contraction, and good dynamic range in a muscle-like form factor. There has been a rapid increase of research efforts devoted to the study of SCP actuators. For rob
Being inherently compliant, the robotic artificial muscles are increasingly popular in applications such as safe human-robot interaction, legged robotics, prostheses and orthoses, and soft robotics. Their full utilization is often challenged by the coupled hysteresis among input, strain, and tension…
This paper presents a deployable boom which combines a rigid telescopic frame and a flexible tape spring. The front end of the spring is fixed on the rear end of the innermost segment of the frame. The spring spreads and rolls up inside the frame to drive the segments to move one by one to realize t…
Currently, the state-of-the-art speaker verification system is based on i-vector and PLDA. However, PLDA requires tens of thousands of development data from many speakers. This makes it difficult to learn the PLDA parameters for a domain with scarce data. In this paper, we propose an effective trans…
For a robot serving in a complex environment such as in a restaurant, it is difficult to perform a task like tabletop object manipulation completely by itself, in that some information may be missing. An approach to deal with this is to use a tele-control system and method to control the robot or de…
Recently there has been great interest in the application of word representation techniques to various natural language processing (NLP) scenarios. Word representation features from techniques such as Brown clustering or spectral clustering are generally computed from large corpora of unlabeled data…