107 accepted papers
The two-dimensional (2D) graph structure of a molecule encodes abundant latent property information. A well-designed molecular graph encoder can capture informative low-dimensional dense representations of molecules, which can subsequently be applied to a widerange of downstream tasks. To achieve fi
Large language models (LLMs) have achieved remarkable progress in open-ended text generation, yet they remain prone to hallucinating incorrect or unsupported content, which undermines their reliability. This issue is exacerbated in long-form generation due to hallucination snowballing, a phenomenon …
The Mixture-of-Experts (MoE) architecture has emerged as a promising paradigm for scaling large language models (LLMs) by activating only a sparse subset of experts per input. However, its massive parameter size remains a major obstacle to efficient deployment. Existing pruning methods often ignore
This work highlights that video world modeling, alongside vision-language pre-training, establishes a distinct foundation for robot learning. By capturing environmental dynamics, video world models enable the robot to “imagine” near future states—a capability essential for effective planning. Inspir…
Offline reinforcement learning (RL) seeks to learn an optimal policy from a fixed dataset, but distributional shift between the dataset and the learned policy often leads to suboptimal real-world performance. Existing methods typically use behavior policy regularization to constrain the learned poli…
Large Language Models (LLMs) exhibit strong capabilities in high-level semantic understanding and strategic planning, yet they suffer from persistent quantitative failure modes, such as imprecise computation and the illusion of quantitative coherence, which limit their reliability in high-stakes dec…
The response behaviors observed in online user-generated content (UGC) frequently demonstrate non-linear characteristics, such as conditional branching and selective avoidance. These patterns present additional challenges for ensuring the trustworthiness of Large Language Model (LLMs) reasoning, par
Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by recombining primitives learned from seen pairs. Recent CZSL methods built on vision-language models (VLMs) typically adopt parameter-efficient fine-tuning (PEFT).They apply visual disentanglers for deco
Recent advancements in multi-robot navigation have explored methods that combine Large Language Models (LLMs) for tasks like scene understanding or high-level decision-making. However, these approaches face challenges with high inference latency and potential hallucinations. To address these challen
Recent advances in vision–language models (VLMs) have shed light on human-level embodied intelligence. However, existing benchmarks for VLM-driven embodied agents still rely on high-level commands or discretised action spaces—``non-native
Existing solutions for bundle recommendation (BR) have achieved remarkable effectiveness for predicting the user’s preference for prebuilt bundles. However, bundle-item (B-I) affiliation will vary dynamically in real scenarios. For ex ample, a bundle themed as ‘casual outfit’ may add ‘hat’ or re
Current audio-visual speech separation (AVSS) models typically rely on implicit multimodal fusion, but the absence of explicit modality alignment and reliability modeling often causes semantic misalignment and contaminates speech representations. The brain addresses this with a hierarchy: top-down a…
Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical factor for real-world applications. Yet an overlooked threat is Reasoning-Level Denial-of-Service (R-DoS), in which an attacker preserves task correc…
Continual knowledge graph embedding (CKGE) has gained popularity for managing dynamic knowledge graphs. Unlike general graph continual-learning approaches, CKGE focuses on retaining triple-level knowledge, thereby overcoming the inability of static models to accommodate continuously arriving facts.
3D visual grounding (VG) aims to localize target objects in 3D scenes based on free-form textual descriptions. Existing 3D VG models predominantly employ point-based backbones for point cloud feature extraction. Such methods require aggressive downsampling of the input point cloud, which sacrifices
Recent advances in cross-modal few-shot adaptation treat visual-semantic alignment as a continuous feature transport problem via Flow Matching (FM). However, we argue that Euclidean-based FM overlooks fundamental limitations of flat geometry, where polynomial volume growth fails to accommodate diver…
Personalized image generation aims to produce images of user-specified concepts while enabling flexible editing. Recent training-free approaches, while exhibiting higher computational efficiency than training-based methods, struggle with identity preservation, applicability, and compatibility with d
Generalization remains a central challenge in offline reinforcement learning (RL), where policies are trained solely from static datasets and must perform reliably under distribution shift. While most existing offline RL methods focus on reducing training loss using standard optimizers such as Adam,…
Recent advances in multi-modal large language models (MLLMs) have significantly improved object-level grounding and region captioning. However, they remain limited in visual relation understanding, struggling even with binary relation detection, let alone N-ary relations involving multiple semantic
Time series is a pervasive data type across various application domains, rendering the reasonable solving of diverse time series tasks a long-standing goal. Recent advances in large language models (LLMs), especially their reasoning abilities unlocked through reinforcement learning (RL), have opened…
Noisy labels are inevitable in real-world datasets. These noisy labels cause deep neural networks to gradient descent towards the wrong direction, leading to performance degradation. In this paper, We propose an efficient method for filtering out noisy labels during training. We calculate an embeddi…
Bearing-only Target Motion Analysis (TMA) is a promising technique for passive tracking in various applications as a bearing angle is easy to measure. Despite its advantages, bearing-only TMA is challenging due to the nonlinearity of the bearing measurement model and the lack of range information, w
Knowledge Graphs (KGs) have revolutionized structured knowledge representation, yet their capacity to model real-world complexity and heterogeneity remains fundamentally constrained. The emerging paradigm of Multi-View Knowledge Graphs (MVKGs) addresses this gap through multi-view learning, but exis
Does seeing always mean knowing? Large Vision-Language Models (LVLMs) integrate separately pre-trained vision and language components, often using CLIP-ViT as vision backbone. However, these models frequently encounter a core issue of "cognitive misalignment" between the vision encoder (VE) and the…
Interleaved image-text generation has emerged as a crucial multimodal task, aiming at creating sequences of interleaved visual and textual content given a query. Despite notable advancements in recent multimodal large language models (MLLMs), generating integrated image-text sequences that exhibit n…
A cooperative circumnavigation framework is proposed for multi-quadrotor systems to enclose and track a moving target without reliance on external localization systems. The distinct relationships between quadrotor-quadrotor and quadrotor-target interactions are evaluated using a heterogeneous percep
The Mixture of Experts (MoE) model is a promising approach for handling code-switching speech recognition (CS-ASR) tasks. However, the existing CS-ASR work on MoE has yet to leverage the advantages of MoE’s parameter scaling ability fully. This work proposes DLG-MoE, a Dynamic Language Group-based M…
Offline reinforcement learning confronts the distributional shift challenge, a consequence of learning policy from static datasets. Current methods primarily handle this issue by aligning the learned policy with the behavior policy or conservatively estimating Q-values for out-of-distribution (OOD)…
The imperative of user privacy protection and regulatory compliance necessitates sensitive data removal in model training, yet this process often induces distributional shifts that undermine model performance-particularly in out-of-distribution (OOD) scenarios. We propose a novel data removal approa…
The local extremum is a crucial factor that affects the efficiency of online coverage path planning (CPP). Most online CPP methods generate coverage motions point by point in unknown environments. However, these solutions ignore efficient global coverage and probably result in local extremum. This l
Dealing with the distribution shift is a significant challenge when building offline reinforcement learning (RL) models that can generalize from a static dataset to out-of-distribution (OOD) scenarios. Previous approaches have employed pessimism or conservatism strategies. More recently, data-driven…
Domain generalization (DG) aims to train models on multiple source domains to generalize effectively to unseen target domains, addressing performance degradation caused by domain shifts. Many existing methods rely on direct feature alignment, which disrupts natural sequence relationships, causes mis
Open-vocabulary scene graph generation (OVSGG) extends traditional SGG by recognizing novel objects and relationships beyond predefined categories, leveraging the knowledge from pre-trained large-scale models. Existing OVSGG methods always adopt a two-stage pipeline: 1) Infusing knowledge into large…
Multi-agent reinforcement learning (MARL) has demonstrated remarkable success in collaborative tasks, yet faces significant challenges in scaling to complex scenarios requiring sustained planning and coordination across long horizons. While hierarchical approaches help decompose these tasks, they ty
Graph Convolutional Networks (GCNs) demonstrate significant potential in recommendation systems but face difficulties with the cold-start problem, especially in integrating new nodes during inference. The typical solution leverages meta-learning for few-shot learning, though it often fails to fully…
As an important fine-grained sentiment analysis task, aspect sentiment triplet extraction (ASTE) aims to identify three elements, i.e., aspect, opinion and sentiment polarity as a triplet. Advanced ASTE researches have mostly explored triplet-wise ability to achieve superior improvement. However, ex…
Soft robotics, renowned for its robust adaptability to complex environments, holds great promise for a wide array of applications. Among the various actuation methods, magnetic fields stand out as particularly advantageous for soft robotics due to their ability to enable remote control and their bio
Reinforcement learning from human feedback (RLHF) offers a promising approach to aligning large language models (LLMs) with human preferences. Typically, a reward model is trained or supplied to act as a proxy for humans in evaluating generated responses during the reinforcement training phase. Howe
When fine-tuning pre-trained Large Language Models (LLMs) to align with human values and intentions, maximizing the estimated reward can lead to superior performance, but it also introduces potential risks due to deviations from the reference model's intended behavior. Most existing methods typicall…
Recently, flow matching based speech synthesis has significantly enhanced the quality of synthesized speech while reducing the number of inference steps. In this paper, we introduce SlimSpeech, a lightweight and efficient speech synthesis system based on rectified flow. We have built upon the existi…
Molecular Relational Learning (MRL) is widely applied in molecular sciences. Recent studies attempt to retain molecular core information (e.g., substructures) by Graph Information Bottleneck but primarily focus on information compression without considering the causal dependencies of chemical reacti
Materials science text mining (MSTM), involving tasks like property extraction and synthesis action retrieval, is pivotal for advancing research by deriving critical insights from scientific literature. Descriptors, serving as essential task labels, often vary in meaning depending on researchers' us…
Place recognition is a challenging but crucial task in robotics. Current description-based methods may be limited by representation capabilities, while pairwise similarity-based methods require exhaustive searches, which is time-consuming. In this paper, we present a novel coarse-to-fine approach to…
With the development of deep learning, speaker recognition systems have shown increasingly better performance. The generalization ability of the models is also an important aspect of performance evaluation. Typically, a baseline system is used to compare against the improved models to demonstrate pe…
Reactive planning enables the robots to deal with dynamic events in uncertain environments. However, existing methods heavily rely on the predefined hard-coded robot behaviors, e.g, a pre-coded temporal logic formula that specifies how robot should react. Little attention has been paid for autonomou…
Numerous studies have emphasized the application of autonomous intelligence in human-robot shared control to enhance surgical convenience and efficiency. However, the neglect of human dominance may reduce surgical safety. This paper developed a safety-enhanced human-robot shared control method by in…
It is challenging to coordinately allocate and plan the tasks of a heterogeneous multi-agent system in a shared workspace. It can be even more challenging if the agents are subject to limited communication capability (i.e., exchange information with nearby agents only) and complex tasks with tempora
Offline Reinforcement Learning (RL) commonly suffers from the out-of-distribution (OOD) overestimation issue due to the distribution shift. Prior work gradually shifts their focus from suppressing OOD overestimation to avoiding overly conservative learning from suboptimal behavior policies to improv…
End-to-end (E2E) multi-speaker speech recognition with the serialized output training (SOT) strategy demonstrates good performance in modeling diverse speaker scenarios. However, the E2E architecture doesn’t explicitly address the modeling of overlapping speech areas, potentially limiting the model’…
The style transfer task in Text-to-Speech (TTS) refers to the process of transferring style information into text content to generate corresponding speech with a specific style. However, most existing style transfer approaches are either based on fixed emotional labels or reference speech clips, whi…
As an important fine-grained task of sentiment analysis, Aspect-Category based Sentiment Analysis (ACSA) aims to identify the sentiment polarities of pre-defined categories in text. However, due to subjectivity, the highly semantically similar text has polysemous sentiments to different people, lead…
In order to reduce the computational complexity of large language models, great efforts have been made to to improve the efficiency of transformer models such as linear attention and flash-attention. However, the model size and corresponding computational complexity are constantly scaled up in pursu…
Diversifying training data techniques have achieved tremendous success in Domain Generalization (DG) tasks. The key to diversifying domain data is by increasing the types of domain styles. After investigating this issue from the perspective of the Fourier transform, the domain cue is found to be imp…
Existing works have made great progress in improving adversarial robustness, but typically test their method only on data from the same distribution as the training data, i.e. in-distribution (ID) testing. As a result, it is unclear how such robustness generalizes under input distribution shifts, i.…
Large pre-trained Vision-Language Models (VLMs) like CLIP despite having remarkable generalization ability are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of the text prompt instead of the extensively studied model weight…
The diffusion models including Denoising Diffusion Probabilistic Models (DDPM) and score-based generative models have demonstrated excellent performance in speech synthesis tasks. However, its effectiveness comes at the cost of numerous sampling steps, resulting in prolonged sampling time required t…
Recently, pre-trained models (PTMs) have been extensively applied in speaker verification (SV) and greatly boosted system performance. However, mainstream PTMs currently concentrate on using frame-level universal representations. In this paper, we propose a novel pre-training framework that jointly…
A challenging problem in seeking to bring multi-agent reinforcement learning (MARL) techniques into real-world applications, such as autonomous driving and drone swarms, is how to control multiple agents safely and cooperatively to accomplish tasks. Most existing safe MARL methods learn the centrali…
This works exploits soft constraints in linear temporal logic task planning to enhance the agent’s capability in handling potentially conflicting or even infeasible tasks. Different from most existing works that focus on sticking to the original plan and trying to find a relaxed plan if the workspac…
Unsupervised multimodal machine translation (UMMT) aims to leverage vision information as a pivot between two languages to achieve better performance on low-resource language pairs. However, there is presently a challenge: how to handle alignment between distant language pairs (DLPs) in UMMT. To thi…
Security practitioners maintain vulnerability reports (e.g., GitHub Advisory) to help developers mitigate security risks. An important task for these databases is automatically extracting structured information mentioned in the report, e.g., the affected software packages, to accelerate the defense…
Recent advances in vision-language models like Stable Diffusion have shown remarkable power in creative image synthesis and editing.However most existing text-to-image editing methods encounter two obstacles: First the text prompt needs to be carefully crafted to achieve good results which is not in…
As a crucial task in natural language processing, sentiment analysis is widely applied in different fields. However, various implicit expressions interspersed in explicit expressions have become a stumbling block for the further improvement of sentiment analysis. Existing studies usually introduce e…
Pairwise point cloud registration is a critical task for many applications, which heavily depends on finding correct correspondences from the two point clouds. However, the low overlap between input point clouds causes the registration to fail easily, leading to mistaken overlapping and mismatched c…
Video captioning aims to generate sentences to accurately describe the video content, in which video background plays the role of prompts. State-of-the-art methods tend to explore richer video representations adequately, fusing with language to improve caption quality, which has shown great success.…
Tag recommendation in software information sites is a significant task to help developers make distinctions among software objects. Most existing methods usually ignore the semantic information of code snippets in software information sites. To tackle this issue, we regard the code as a semantic enh…
Dubins coverage has been extensively researched to address the coverage path planning (CPP) problem of a known environment for the curvature-constrained robot. However, its fixed-speed assumption prevents the robot from accelerating to reduce the time and limits its flexibility to avoid obstacles. T…
The clustering algorithm plays a crucial role in speaker diarization systems. However, traditional clustering algorithms suffer from the complex distribution of speaker embeddings and lack of digging potential relationships between speakers in a session. We propose a novel graph-based clustering app…
Scene Graph Generation (SGG) aims to detect all the visual relation triplets <sub, pred, obj> in a given image. With the emergence of various advanced techniques for better utilizing both the intrinsic and extrinsic information in each relation triplet, SGG has achieved great progress over the recen…
Recent advances in neural theorem-proving resort to large language models and tree searches. When proving a theorem, a language model advises single-step actions based on the current proving state and the tree search finds a sequence of correct steps using actions given by the language model. Howeve…
Adversarial training suffers from the issue of robust overfitting, which seriously impairs its generalization performance. Data augmentation, which is effective at preventing overfitting in standard training, has been observed by many previous works to be ineffective in mitigating overfitting in adv…
Target-Oriented Multimodal Sentiment Classification (TMSC) aims to perform sentiment polarity on a target jointly considering its corresponding multiple modalities including text, image, and others. Current researches mainly work on either of two types of targets in a decentralized manner. One type…
This work develops a fast task allocation framework for heterogeneous multi-robot systems subject to both temporal logic and inter-task constraints. The considered inter-task constraints include unrelated tasks, compatible tasks, and exclusive tasks. To specify such inter-task relationships, we exte
Current sentence-level evidence extraction based methods may lose the discourse coherence of legal articles since they tend to make the extracted sentences scattered over the article. To solve the problem, this paper proposes a Cascaded Answer-guided key segment learning framework for long Legal ar…
Remarkable progress has been achieved by current depth completion approaches, which produce dense depth maps from sparse depth maps and corresponding color images. However, the performances of these approaches are limited due to the insufficient feature extractions and fusions. In this work, we prop
Recent studies have demonstrated that local training data in Federated Learning can be recovered from gradients, which are called gradient inversion attacks. These attacks display powerful effects on either computer vision or natural language processing tasks. As it is known that there are certain c…
Model Agnostic Meta-Learning (MAML) is an effective meta-learning algorithm for low-resource automatic speech recognition (ASR). It uses gradient descent to learn the initialization parameters of the model through various languages, making the model quickly adapt to unseen low-resource languages. Bu…
Propaganda, commonly used in memes disinformation, can influence the thinking of the audience and increase the reach of communication. Usually logical fallacy, as a kind of popular expression of memes, aims to create a logical reasonable illusion where the conclusion cannot be drawn with the use of…
Reinforcement learning (RL) has made significant progress in areas such as Atari games and robotic control, where the agents have perfect sensing capabilities. However, in many real-world sequential decision-making tasks, the observation data could be noisy or incomplete due to the intrinsic low qua…
Automated theorem proving (ATP) has become an appealing domain for exploring the reasoning ability of the recent successful generative language models. However, current ATP benchmarks are mainly focus on symbolic inference, but rarely involve the understanding of complex number combination reasoni…
In this paper, we present our work in track 2 of the Multi-modal Information based Speech Processing (MISP) 2022 Challenge. We built a cascaded system and explored different acoustic front-ends and end-to-end speech recognition back-ends based on multimodal. To promote effective fusion between the d…
Transformer has achieved extraordinary performance in Natural Language Processing and Computer Vision tasks thanks to its powerful self-attention mechanism, and its variant Conformer has become a state-of-the-art architecture in the field of Automatic Speech Recognition (ASR). However, the main-stre…
Bundle recommendation suggests a set of items to users against their complex needs, where user-bundle interaction learning is key. It is observed that Gromov’s δ-hyperbolicity of the interaction graph in bundle recommendation is smaller (lower is more hyperbolic) than those in traditional item recom…
Recently, the fine-tuning pre-trained model framework has emerged as a promising paradigm for speech-processing tasks. In this study, we present a novel strategy for unsupervised speaker verification using the Sub-structure of Pre-Trained Model (Sub-PTM), which consists of a CNN-based feature extrac…
Pretrained vision-language models, such as CLIP, have demonstrated strong generalization capabilities, making them promising tools in the realm of zero-shot visual recognition. Visual relation detection (VRD) is a typical task that identifies relationship (or interaction) types between object pairs…
Currently, researchers focus on generating codes from the requirement documents. However, current approaches still perform poorly on some requirements needing complex problem-solving skills. In reality, to tackle such complex requirements, instead of directly translating requirement documents into c…
How to get a good value estimation is one of the key problems in reinforcement learning (RL). Current off-policy methods, such as Maxmin Q-learning, TD3 and TADD, suffer from the underestimation problem when solving the overestimation problem. In this paper, we propose the Quasi-Median Operation, a…
Unsupervised clustering on speakers is becoming increasingly important for its potential uses in semi-supervised learning. In reality, we are often presented with enormous amounts of unlabeled data from multi-party meetings and discussions. An effective unsupervised clustering approach would allow u…
Recent advances in cross-lingual text-to-speech (TTS) made it possible to synthesize speech in a language foreign to a monolingual speaker. However, there is still a large gap between the pronunciation of generated cross-lingual speech and that of native speakers in terms of naturalness and intellig…
LiDAR-based place recognition (LPR) is one of the basic capabilities of robots, which can retrieve scenes from maps and identify previously visited locations based on 3D point clouds. As robots often pass the same place from different views, LPR methods are supposed to be robust to rotation, which i
Unbiased SGG has achieved significant progress over recent years. However, almost all existing SGG models have overlooked the ground-truth annotation qualities of prevailing SGG datasets, i.e., they always assume: 1) all the manually annotated positive samples are equally correct; 2) all the un-anno…
Evaluating the high-effect factors of citizens' happiness is beneficial to a wide range of policy-making for economics and politics in most countries. Benefiting from the high-efficiency of regression models, previous efforts by sociology scholars have analyzed the effect of happiness factors with h…
In this paper, we introduce a new open source toolkit for automatic speaker verification (ASV), named ASV-Subtools. Adopting PyTorch as main deep learning engine and Kaldi toolkit for data processing, ASV-Subtools allows users to develop modern speaker recognizers flexibly and efficiently. The toolk…
Transformer is a new kind of calculation paradigm for deep learning which has shown strong performance on a large variety of computer vision tasks. However, compared with conventional deep models (e.g., convolutional neural networks), vision transformers require more computational resources which ca…
The principal way of performing user profiling is to investigate accumulated social media data. However, the problem of information asymmetry generally exists in user generated contents since users post multi-modal contents in social media freely. In this paper, we propose a novel text-image coopera…
Anaphora and ellipses are two common phenomena in dialogues. Without resolving referring expressions and information omission, dialogue systems may fail to generate consistent and coherent responses. Traditionally, anaphora is resolved by coreference resolution and ellipses by query rewrite. In this…
End-to-end speech recognition has achieved good recognition performance on standard English pronunciation datasets. However, one prominent problem with end-to-end speech recognition systems is that non-native English speakers tend to have complex and varied accents, which reduces the accuracy of Eng…
Math word problem (MWP) is a challenging and critical task in natural language processing. Many recent studies formalize MWP as a generation task and have adopted sequence-to-sequence models to transform problem descriptions to mathematical expressions. However, mathematical expressions are prone to…
With the development of deep learning, end-to-end neural text-to-speech (TTS) systems have achieved significant improvements in high-quality speech synthesis. However, most of these systems are attention-based autoregressive models, resulting in slow synthesis speed and large model parameters. In ad…
Named Entity Recognition (NER) and Entity Linking (EL) play an essential role in voice assistant interaction, but are challenging due to the special difficulties associated with spoken user queries. In this paper, we propose a novel architecture that jointly solves the NER and EL tasks by combining…
LiDAR-based SLAM system is admittedly more accurate and stable than others, while its loop closure detection is still an open issue. With the development of 3D semantic segmentation for point cloud, semantic information can be obtained conveniently and steadily, essential for high-level intelligence…
Place recognition gives a SLAM system the ability to correct cumulative errors. Unlike images that contain rich texture features, point clouds are almost pure geometric information which makes place recognition based on point clouds challenging. Existing works usually encode low-level features such…
Recent studies show that word embedding models often underestimate similarities between similar words and overestimate similarities between distant words. This results in word similarity results obtained from embedding models inconsistent with human judgment. Manifold learning-based methods are wide…
Video-based Autism Spectrum Disorder (ASD) detection is a challenge to most video classification networks due to the high degree of similarity between categories. Bilinear pooling is a second-order method, which is widely used in fine-grained visual recognition. However, the average summation in bil…
Under noisy environments, to achieve the robust performance of speaker recognition is still a challenging task. Motivated by the promising performance of multi-task training in a variety of image processing tasks, we explore the potential of multitask adversarial training for learning a noise-robust…
This paper investigates the on-line analysis of high-frequency financial order book data using Bayesian modelling techniques. Order book data involves evolving queues of orders at different prices, and here we propose that the order book shape is proportional to a gamma or inverse-gamma density func…
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…