Related papers: Progressive Language-guided Visual Learning for Mu…

Recent vision-language-action (VLA) models for multi-task robot manipulation often rely on fixed camera setups and shared visual encoders, which limit their performance under occlusions and during cross-task transfer. To address these…

While mainstream vision-language models (VLMs) have advanced rapidly in understanding image level information, they still lack the ability to focus on specific areas designated by humans. Rather, they typically rely on large volumes of…

Pre-trained vision-language models (VLMs) have shown remarkable generalization capabilities via prompting, which leverages VLMs as knowledge bases to extract information beneficial for downstream tasks. However, existing methods primarily…

Low-level vision involves a wide spectrum of tasks, including image restoration, enhancement, stylization, and feature extraction, which differ significantly in both task formulation and output domains. To address the challenge of unified…

Effective pest recognition and management are crucial for sustainable agricultural development. However, collecting pest data in real scenarios is often challenging. Compared to other domains, pests exhibit a wide variety of species with…

Recent Vision-Language-Action (VLA) models built on pre-trained Vision-Language Models (VLMs) require extensive post-training, resulting in high computational overhead that limits scalability and deployment.We propose CogVLA, a…

Typical large vision-language models (LVLMs) apply autoregressive supervision solely to textual sequences, without fully incorporating the visual modality into the learning process. This results in three key limitations: (1) an inability to…

Visual commonsense reasoning (VCR) is a challenging multi-modal task, which requires high-level cognition and commonsense reasoning ability about the real world. In recent years, large-scale pre-training approaches have been developed and…

Video grounding aims to localize the corresponding video moment in an untrimmed video given a language query. Existing methods often address this task in an indirect way, by casting it as a proposal-and-match or fusion-and-detection…

This paper is concerned with multi-view reinforcement learning (MVRL), which allows for decision making when agents share common dynamics but adhere to different observation models. We define the MVRL framework by extending partially…

Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention…

The Vision-and-Language Navigation (VLN) task requires an agent to follow natural language instructions and navigate through complex environments. Existing MLLM-based VLN methods primarily rely on imitation learning (IL) and often use…

In the field of multi-modal language models, the majority of methods are built on an architecture similar to LLaVA. These models use a single-layer ViT feature as a visual prompt, directly feeding it into the language models alongside…

Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-language models (VLMs). However, its outcome-level supervision is too coarse to diagnose and…

Language-guided supervision, which utilizes a frozen semantic target from a Pretrained Language Model (PLM), has emerged as a promising paradigm for visual Continual Learning (CL). However, relying on a single target introduces two critical…

Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video, emphasizing modeling dense text-video relations. The current RVOS methods typically use independently pre-trained vision…

Self-supervised learning methods such as wav2vec 2.0 have shown promising results in learning speech representations from unlabelled and untranscribed speech data that are useful for speech recognition. Since these representations are…

Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR approaches typically rely on outcome-driven optimization that…

GUI grounding, which translates natural language instructions into precise pixel coordinates, is essential for developing practical GUI agents. However, we observe that existing grounding models exhibit significant coordinate prediction…

Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in connecting vision and language, yet their proficiency in fundamental visual reasoning tasks remains limited. This limitation can be attributed to…