Related papers: VisionCoach: Reinforcing Grounded Video Reasoning …

Visual Commonsense Reasoning (VCR), deemed as one challenging extension of the Visual Question Answering (VQA), endeavors to pursue a more high-level visual comprehension. It is composed of two indispensable processes: question answering…

Video understanding plays a vital role in bridging low-level visual signals with high-level cognitive reasoning, and is fundamental to applications such as autonomous driving, embodied AI, and the broader pursuit of AGI. The rapid…

Large Vision-Language Models (VLMs) excel at general visual reasoning tasks but exhibit sharp performance degradation when applied to novel domains with substantial distribution shifts from pretraining data. Existing domain adaptation…

Reinforcement learning (RL) provides a principled framework for improving Vision-Language Models (VLMs) on complex reasoning tasks. However, existing RL approaches often rely on human-annotated labels or task-specific heuristics to define…

Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary…

Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, existing methods face spatial…

Visual model-based RL methods typically encode image observations into low-dimensional representations in a manner that does not eliminate redundant information. This leaves them susceptible to spurious variations -- changes in…

Training language models to produce both correct answers and sound reasoning remains an open challenge. Reinforcement learning with verifiable rewards typically optimizes only final outcomes, which can lead to a failure mode where task…

Large vision-and-language models (VLMs) trained to match images with text on large-scale datasets of image-text pairs have shown impressive generalization ability on several vision and language tasks. Several recent works, however, showed…

Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks. However, it remains unclear whether the superior performance of VLMs stems from genuine…

DeepSeek-R1-Zero has successfully demonstrated the emergence of reasoning capabilities in LLMs purely through Reinforcement Learning (RL). Inspired by this breakthrough, we explore how RL can be utilized to enhance the reasoning capability…

Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasoning remains unstable. Repeated sampling over the same input often produces divergent reasoning…

Visual and textual soft prompt tuning can effectively improve the adaptability of Vision-Language Models (VLMs) in downstream tasks. However, fine-tuning on video tasks impairs the model's generalization ability to unseen classes. Existing…

In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive…

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…

Visual prompting infuses visual information into the input image to adapt models toward specific predictions and tasks. Recently, manually crafted markers such as red circles are shown to guide the model to attend to a target region on the…

Transformer-based architectures have recently demonstrated remarkable performance in the Visual Question Answering (VQA) task. However, such models are likely to disregard crucial visual cues and often rely on multimodal shortcuts and…

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models, yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection,…

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language tasks yet remain limited in long video understanding due to the limited context window. Consequently, prevailing approaches tend to rely on…

Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely focused on single-image or temporally dense video settings. In…