Related papers: The Role of Entropy in Visual Grounding: Analysis …

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Entropy Regularisation is a widely adopted technique that enhances policy optimisation performance and stability. A notable form of entropy regularisation is augmenting the objective with an entropy term, thereby simultaneously optimising…

Software engineering presents complex, multi-step challenges for Large Language Models (LLMs), requiring reasoning over large codebases and coordinated tool use. The difficulty of these tasks is exemplified by benchmarks like SWE-bench,…

Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Action frameworks. However, a significant gap remains between the high-level semantic focus…

Embodied navigation agents built upon large reasoning models (LRMs) can handle complex, multimodal environmental input and perform grounded reasoning per step to improve sequential decision-making for long-horizon tasks. However, a critical…

"Thinking with images" has emerged as an effective paradigm for advancing visual reasoning, extending beyond text-only chains of thought by injecting visual evidence into intermediate reasoning steps. However, existing methods fall short of…

Recent research has shown that CLIP models struggle with visual reasoning tasks that require grounding compositionality, understanding spatial relationships, or capturing fine-grained details. One natural hypothesis is that the CLIP vision…

While multimodal large language models (MLLMs) have made groundbreaking progress in embodied intelligence, they still face significant challenges in spatial reasoning for complex long-horizon tasks. To address this gap, we propose…

Empathetic response generation is a desirable aspect of conversational agents, crucial for facilitating engaging and emotionally intelligent multi-turn conversations between humans and machines. Leveraging large language models for this…

Efficient processing of high-resolution images is crucial for real-world vision-language applications. However, existing Large Vision-Language Models (LVLMs) incur substantial computational overhead due to the large number of vision tokens.…

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…

Large language models (LLMs) have proven their remarkable versatility in handling a comprehensive range of language-centric applications. To expand LLMs' capabilities to a broader spectrum of modal inputs, multimodal large language models…

When applying reinforcement learning--typically through GRPO--to large vision-language model reasoning struggles to effectively scale reasoning length or generates verbose outputs across all tasks with only marginal gains in accuracy. To…

Visual grounding seeks to localize the image region corresponding to a free-form text description. Recently, the strong multimodal capabilities of Large Vision-Language Models (LVLMs) have driven substantial improvements in visual…

Large Language Models (LLMs) suffer significant performance degradation in multi-turn conversations when information is presented incrementally. Given that multi-turn conversations characterize everyday interactions with LLMs, this…

Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge to downstream robot control. Yet current diffusion-based…

Recently, Agentic Reinforcement Learning (Agentic RL) has made significant progress in incentivizing the multi-turn, long-horizon tool-use capabilities of web agents. While mainstream agentic RL algorithms autonomously explore…

Domain-specific large language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized datasets, represent a significant advancement in applied AI. A common strategy in LLM fine-tuning is…

Alignment of large language models (LLMs) with human preferences typically relies on supervised reward models or external judges that demand abundant annotations. However, in fields that rely on professional knowledge, such as medicine and…

Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs). Considering existing RL-based finetuning methods, entropy intervention turns out to be an effective…