80 accepted papers
Vision-language-action models (VLAs) use an end-to-end learning architecture, which can realize the integration of visual perception, semantic understanding and motion control. However, when tackling with the dynamic or long-horizon tasks, VLAs have poor robustness and real-time adjustment ability a
Existing studies on bias mitigation methods for large language models (LLMs) use diverse baselines and metrics to evaluate debiasing performance, leading to inconsistent comparisons among them. Moreover, their evaluations are mostly based on the comparison between LLMs' probabilities of biased and u…
Federated domain generalization in person re-identification (FedDG-ReID) aims to learn a privacy-preserving server model from decentralized client source domains that generalizes to unseen domains. Existing approaches enhance the generalizability of the server model by increasing the diversity of c
Adversarial Imitation Learning (AIL) is a prominent paradigm in imitation learning that enables policy acquisition from expert demonstrations without relying on manually crafted reward functions. Although AIL has achieved promising results in certain scenarios, many existing methods suffer from mode…
Long-horizon robotic manipulation remains a critical challenge in robotics. Hierarchical reinforcement learning offers a promising solution, but often suffers from an imbalance dilemma: simplifying skill learning increases the complexity of planning, thereby expanding the solution space and computat…
The application of federated domain generalization in person re-identification (FedDG-ReID) aims to enhance the model
Federated Domain Generalization for Person Re-Identification (FedDG-ReID) aims to learn domain-invariant representations from decentralized data. Although Vision Transformers (ViTs) are widely adopted, their global attention often fails to distinguish pedestrians from high similarity backgrounds or
Low-Light Image Enhancement (LLIE) task aims at improving contrast while restoring details and textures for images captured in low-light conditions. HVI color space has made significant progress in this task by enabling precise decoupling of chrominance and luminance. However, for the interaction of
Chinese opera is celebrated for preserving classical art. However, early filming equipment limitations have degraded videos of last-century performances by renowned artists (e.g., low frame rates and resolution), hindering archival efforts. Although space-time video super-resolution (STVSR) has adva
Mathematical reasoning represents a critical frontier in advancing large language models (LLMs). While step-by-step approaches have emerged as the dominant paradigm for mathematical problem-solving in LLMs, the quality of reasoning steps in training data fundamentally constrains model performance. R…
Deploying robots in open‑ended real‑world environments demands continual learning capabilities to adapt to an ever-expanding range of tasks. This requires retaining previously acquired skills without forgetting while effectively leveraging prior knowledge to learn new ones. Inspired by neuroscience,…
Recent advances in reasoning capabilities of large language models (LLMs) are largely driven by reinforcement learning (RL), yet the underlying parameter dynamics during RL training remain poorly understood. This work identifies two fundamental properties of RL-induced parameter updates in LLMs: (1)…
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 …
Enhancing the multimodal reasoning capabilities of Multimodal Large Language Models (MLLMs) is a challenging task that has attracted increasing attention in the community. Recently, several studies have applied Reinforcement Learning with Verifiable Rewards (RLVR) to the multimodal domain in order t…
Underwater images commonly suffer from foreground-background ambiguity, loss of structural details, and severely reduced contrast, which collectively make underwater object detection (UOD) an inherently challenging task. To handle this issue, we present a residual-guided hierarchical calibration net
This paper presents a model-based reinforcement learning (MBRL) approach with a receding horizon mechanism to optimize the lateral trajectory-tracking performance of autonomous vehicles (AVs). Accurate modeling of complex vehicle dynamics and adaptation to dynamic environments with limited data pose…
Existing cross-modal pedestrian detection (CMPD) employs complementary information from RGB and thermal-infrared (TIR) modalities to detect pedestrians in 24h-surveillance systems. RGB captures rich pedestrian details under daylight, while TIR excels at night. However, TIR focuses primarily on the p
Open-vocabulary semantic segmentation extends pixel-level recognition to arbitrary text-described categories. Despite strong global semantic understanding, vision-language models such as CLIP exhibit limited spatial precision and semantic ambiguity across large vocabularies, constraining their effec
Many classic opera videos exhibit poor visual quality due to the limitations of early filming equipment and long-term degradation during storage. Although real-world video super-resolution (RWVSR) has achieved significant advances in recent years, directly applying existing methods to degraded opera
Reinforcement Learning with Verifiable Reward (RLVR) effectively solves complex tasks but demands extremely long context lengths during training, leading to substantial computational costs. While multi-stage training can partially mitigate this, starting with overly short contexts often causes irrev…
Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitrarily accelerated, cheaply reset, or massively replicated, which makes scalable data collection, heterogeneous deployment, a…
Closed-set object detection in remote sensing imagery has made significant progress, but achieving high detection accuracy remains challenging. Vision-Language Models (VLMs), which possess rich prior knowledge, offer a promising solution to this challenge. However, most existing VLMs are designed fo
Large reasoning models such as OpenAI o1 and DeepSeek-R1 have demonstrated remarkable performance in complex reasoning tasks. A critical component of their training is the incorporation of reference-based reward systems within reinforcement learning (RL), where model outputs are evaluated against gr…
The scarcity of large-scale, open-source data for dialects severely hinders progress in speech technology, a challenge particularly acute for the widely spoken Sichuanese dialects of Chinese. To address this critical gap, we introduce WenetSpeech-Chuan, a 10,000-hour, richly annotated corpus constru…
The development of speech understanding and generation has been significantly accelerated by the availability of large-scale, high-quality speech datasets. Among these, ASR and TTS are regarded as the most established and fundamental tasks. However, for Cantonese (Yue Chinese), spoken by approximate
Unmanned aerial–aquatic vehicles (UAAVs) provide cross-domain adaptability and broad visions, while autonomous underwater vehicles (AUVs) support long-duration operations. This work integrates the two by developing a rapid underwater docking and releasing system. An autonomous clamping mechanism is …
With success in image generation, generative diffusion models are increasingly adopted for discriminative scenarios because generating pixels is a unified and natural perception interface. Although directly re-purposing their generative denoising process has established promising progress in special…
Chinese, as a linguistic system rich in depth and complexity, is characterized by distinctive elements such as ancient poetry, proverbs, idioms, and other cultural constructs. However, current Large Language Models (LLMs) face limitations in these specialized domains, highlighting the need for the d…
Math Word Problems (MWPs) play a vital role in assessing the capabilities of Large Language Models (LLMs), yet current research primarily focuses on questions with concise contexts. The impact of longer contexts on mathematical reasoning remains under-explored. This study pioneers the investigation…
Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs). Previous studies have developed various extensions of CoT, which focus primarily on enhancing end-task performance. In addition, there has been research on a
In offline reinforcement learning, value overestimation caused by out-of-distribution (OOD) actions significantly limits policy performance. Recently, diffusion models have been leveraged for their strong distribution-matching capabilities, enforcing conservatism through behavior policy constraints.
Video-based person re-identification (ReID) has become increasingly important due to its applications in video surveillance applications. By employing events in video-based person ReID, more motion information can be provided between continuous frames to improve recognition accuracy. Previous approa…
One-shot subset selection serves as an effective tool to reduce deep learning training costs by identifying an informative data subset based on the information extracted by an information extractor (IE). Traditional IEs, typically pre-trained on the target dataset, are inherently dataset-dependent.…
Modern Large Language Models, such as the LLaMA, Qwen and DeepSeek series, predominantly adopt the Pre-LayerNorm (Pre-LN) Transformer architecture. While being stable during pretraining and scalable to large model sizes, Pre-LN suffers from an exponential growth in activation variance across layers,…
The agile maneuvering control of autonomous vehicles (AVs) requires the tracking of reference trajectories characterized by high acceleration, sharp curvature, considerable disturbances, and significant time-varying, all while ensuring stability and accuracy. The inherent uncertainty and time-varyin
The technology for generating music from textual descriptions has seen rapid advancements. However, evaluating text-to-music (TTM) systems remains a significant challenge, primarily due to the difficulty of balancing performance and cost with existing objective and subjective evaluation methods. In…
Soft robots are promising to offer flexibility in environmental interaction tasks through compliant deformations. However, the infinite degrees of freedom and high nonlinearity of dynamics pose significant challenges in dynamic modeling and control in soft robots. While online reinforcement learning
Self-correction is a novel method that can stimulate the potential reasoning abilities of large language models (LLMs). It involves detecting and correcting errors during the inference process when LLMs solve reasoning problems. However, recent works do not regard self-correction as a spontaneous an…
Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as process reward models (PRMs) or self-consistency operate as…
Humans excel at reusing prior knowledge to address new challenges and developing skills while solving problems. This paradigm becomes increasingly popular in the development of autonomous agents, as it develops systems that can self-evolve in response to new challenges like human beings. However, pr…
Nighttime Semantic Segmentation (NSS) is essential to many cutting-edge vision applications. However, existing technologies overly rely on massive labeled data, whose annotation is time-consuming and laborious. In this paper, we pioneer a new task focusing on exploring the potential of training stra…
Unsupervised visible-infrared person re-identification (US-VI-ReID) seeks to match infrared and visible images of the same individual without the use of annotations. Current methods typically derive cross-modal correspondences through a single global feature matching process for generating pseudo la…
Large Language Models (LLMs) have made significant strides in mathematical reasoning, underscoring the need for a comprehensive and fair evaluation of their capabilities. However, existing benchmarks often fall short, either lacking extensive coverage of undergraduate-level mathematical problems or…
Large language models (LLMs) have demonstrated remarkable capabilities in solving complex reasoning tasks, particularly in mathematics. However, the domain of physics reasoning presents unique challenges that have received significantly less attention. Existing benchmarks often fall short in evaluat…
Cross-view object geo-localization (CVOGL) aims to locate an object of interest in a captured ground- or drone-view image within the satellite image. However, existing works treat ground-view and drone-view query images equivalently, overlooking their inherent viewpoint discrepancies and the spatial…
This paper presents a unified approach to realize versatile distributed maneuvering with generalized formations. Specifically, we decompose the robots' maneuvers into two independent components, i.e., interception and enclosing, which are parameterized by two independent virtual coordinates. Treatin
Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, their reasoning abilities in the multimodal symbolic music domain remain largely unexplored.We introduce WildScore, the first in-the-wild multimodal sy
In offline reinforcement learning, the challenge of out-of-distribution (OOD) is pronounced. To address this, existing methods often constrain the learned policy through policy regularization. However, these methods often suffer from the issue of unnecessary conservativeness, hampering policy improv…
As Natural Language Processing (NLP) systems are increasingly employed in intricate social environments, a pressing query emerges: *Can these NLP systems mirror human-esque collaborative intelligence, in a multi-agent society consisting of multiple large language models (LLMs)?* This paper probes th…
The wavelet transform has emerged as a powerful tool in deciphering structural information within images. And now, the latest research suggests that combining the prowess of wavelet transform with neural networks can lead to unparalleled image deraining results. By harnessing the strengths of both t…
Despite its remarkable performance, RGB-based Multi-human Pose Estimation (MPE) technology has many practical limitations, such as nighttime and smoggy environments. Infrared imaging is a valid substitution in these scenarios but needs an efficient and fast method for MPE. This letter aims to design
Motion planning has been an important research topic in achieving safe and flexible maneuvers for intelligent vehicles. However, it remains challenging to realize efficient and optimal planning in the presence of uncertain model dynamics. In this paper, a sparse kernel-based reinforcement learning (
In this paper, we propose a multi-environment, multi-LiDAR, multi-task dataset to promote the grid map-based navigation capability for autonomous vehicles. The dataset comprises structured and unstructured environmental data captured by different types of LiDAR and contains various challenging scena
Video anomaly detection (VAD) is an essential but challenging task. Existing prevalent methods focus on analyzing the reconstruction or prediction difference between normal and abnormal patterns through multiple deep features, e.g., optic flow. However, these approaches independently use deep featur…
The training of deep learning-based multichannel speech enhancement and source localization systems relies heavily on the simulation of room impulse response and multichannel diffuse noise, due to the lack of large-scale real-recorded datasets. However, the acoustic mismatch between simulated and re…
Tiny object detection is becoming one of the most challenging tasks in computer vision because of the limited object size and lack of information. The label assignment strategy is a key factor affecting the accuracy of object detection. Although there are some effective label assignment strategies f
Structured Complex Task Decomposition (SCTD) is the problem of breaking down a complex real-world task (such as planning a wedding) into a directed acyclic graph over individual steps that contribute to achieving the task, with edges specifying temporal dependencies between steps. SCTD is an i…
Automated reasoning with unstructured natural text is a key requirement for many potential applications of NLP and for developing robust AI systems. Recently, Language Models (LMs) have demonstrated complex reasoning capacities even without any finetuning. However, existing evaluation for automated…
Grasping is at the core of many robotic manipulation tasks. Despite the recent progress, closed-loop grasp planning in stacked scenes is still unsatisfactory, in terms of efficiency, stability, and most importantly, safety. In this letter, we present CSGP, a closed-loop safe grasp planning approach
Autonomous driving has attracted lots of attention in recent years. For some tasks, e.g., trajectory prediction, motion planning, and trajectory tracking, an accurate vehicle model can reduce the difficulty of these tasks and improve task completion performance. Prior works focused on parameter esti…
Most existing Low-Light Image Enhancement (LLIE) methods are primarily designed to improve brightness in dark regions, which suffer from severe degradation in nighttime images. However, these methods have limited exploration in another major visibility damage, the glow effects in real night scenes.…
Remarkable progress has been made on automated reasoning with natural text, by using Large Language Models (LLMs) and methods such as Chain-of-Thought prompting and Selection-Inference. These techniques search for proofs in the forward direction from axioms to the conclusion, which suffers from a co…
We present a new method for open-vocabulary universal image segmentation, which is capable of performing instance, semantic, and panoptic segmentation under a unified framework. Our approach, called MasQCLIP, seamlessly integrates with a pre-trained CLIP model by utilizing its dense features, thereb…
Skeleton-based human action recognition is becoming increasingly important in a variety of fields. Most existing works train a CNN or GCN based backbone to extract spatial-temporal features, and use temporal average/max pooling to aggregate the information. However, these pooling methods fail to cap…
Retouching images is an essential aspect of enhancing the visual appeal of photos. Although users often share common aesthetic preferences, their retouching methods may vary based on their individual preferences. Therefore, there is a need for white-box approaches that produce satisfying results and…
Conventional Knowledge Graph Construction (KGC) approaches typically follow the static information extraction paradigm with a closed set of pre-defined schema. As a result, such approaches fall short when applied to dynamic scenarios or domains, whereas a new type of knowledge emerges. This necessit…
We propose a lightweight system for stereo-matching using embedded graphic processing units (GPUs). The proposed system overcomes the trade-off between accuracy and processing speed in stereo matching, thus further improving the matching accuracy while ensuring real-time processing. The basic idea i…
Distributed model predictive control (DMPC) concerns how to online control multiple robotic systems with constraints effectively. However, the nonlinearity, nonconvexity, and strong interconnections of dynamic system models and constraints can make the real-time and real-world DMPC implementations n…
The diversified top-k weight clique (DTKWC) search problem is an important generalization of the diversified top-k clique (DTKC) search problem with extensive applications, which extends the DTKC search problem by taking into account the weight of vertices. In this paper, we formulate DTKWC search p…
Recent development of speech signal processing, such as speech recognition, speaker diarization, etc., has inspired numerous applications of speech technologies. The meeting scenario is one of the most valuable and, at the same time, most challenging scenarios for the deployment of speech technologi…
"Most state-of-the-art deep neural networks use static inference graphs, which makes it impossible for such networks to dynamically adjust the depth or width of the network according to the complexity of the input data. Different from these static models, depth-adaptive neural networks, e.g. the mul…
The success of supervised deep learning heavily depends on large labeled datasets whose construction is often challenging in medical image analysis. Contrastive learning, a variant of self-supervised learning, is a potential solution to alleviate the strong demand for data annotation. In this work,…
Deep learning networks with deeper layers become a trend for their good performance but lacks the potential for real-time mobile deployment. Another challenge for paired training networks is the limited generalization capacity caused by the sample bias. To overcome these two challenges, we propose a…
The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic spe…
Symmetry is ubiquitous in everyday objects. Humans tend to grasp objects by recognizing the symmetric regions. In this letter, we investigate how symmetry could boost robotic grasp detection. To this end, we present a learning-based method for detecting grasp from single-view RGB-D images. The key i
This paper presents an empirical study to build relation extraction systems in low-resource settings. Based upon recent pre-trained language models, we comprehensively investigate three schemes to evaluate the performance in low-resource settings: (i) different types of prompt-based methods with few…
In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total. We collect the data from YouTube and Podcast, which covers a variety of…
We introduce the concept of geometric stability to the problem of 6D object pose estimation and propose to learn pose inference based on geometrically stable patches extracted from observed 3D point clouds. According to the theory of geometric stability analysis, a minimal set of three planar/cylind…
The Multi-speaker Multi-style Voice Cloning Challenge (M2VoC) aims to provide a common sizable dataset as well as a fair testbed for the benchmarking of the popular voice cloning task. Specifically, we formulate the challenge to adapt an average TTS model to the stylistic target voice with limited d…
Learning manipulation skills from observing human demonstration videos is a promising aspect for intelligent robotic systems. Recent advances in video to command provide an end-to-end approach to translate a video into robot plans. However, the general video captioning methods focus more on the unde…