Related papers: Decouple to Generalize: Context-First Self-Evolvin…

Vision-language modeling (VLM) aims to bridge the information gap between images and natural language. Under the new paradigm of first pre-training on massive image-text pairs and then fine-tuning on task-specific data, VLM in the remote…

Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive…

Vision Language Models (VLMs) are impressive at visual question answering and image captioning. But they underperform on multi-step visual reasoning -- even compared to LLMs on the same tasks presented in text form -- giving rise to…

To build a generalizable Vision-Language-Action (VLA) model with strong reasoning ability, a common strategy is to first train a specialist VLA on robot demonstrations to acquire reliable manipulation skills, and then incorporate mixed…

Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and geometric awareness. This limitation stems from the fact that…

Large vision-language models (VLMs) increasingly adopt post-training techniques such as long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL) to elicit sophisticated reasoning. While these methods exhibit…

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

The application of visual instruction tuning and other post-training techniques has significantly enhanced the capabilities of Large Language Models (LLMs) in visual understanding, enriching Vision-Language Models (VLMs) with more…

Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their…

Existing Vision Language Models (VLMs) architecturally rooted in "flatland" perception, fundamentally struggle to comprehend real-world 3D spatial intelligence. This failure stems from a dual-bottleneck: input-stage conflict between…

Vision-Language Models (VLMs) excel at high-level scene understanding but falter on fine-grained perception tasks requiring precise localization. This failure stems from a fundamental mismatch, as generating exact numerical coordinates is a…

Enabling large language models (LLMs) to utilize search tools offers a promising path to overcoming fundamental limitations such as knowledge cutoffs and hallucinations. Recent work has explored reinforcement learning (RL) for training…

Continual learning of vision-language models (VLMs) focuses on leveraging cross-modal pretrained knowledge to incrementally adapt to expanding downstream tasks and datasets, while tackling the challenge of knowledge forgetting. Existing…

Current Reinforcement Learning (RL) methodologies for Large Language Models (LLMs) often rely on simplistic, outcome-based reward signals (e.g., final answer correctness), which limits the depth of learning from each interaction. This paper…

Reinforcement Fine-Tuning (RFT) with verifiable rewards has advanced large language models but remains underexplored for Vision-Language (VL) models. The Vision-Language Reward Model (VL-RM) is key to aligning VL models by providing…

Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video…

Since the advent of Large Language Models (LLMs), efforts have largely focused on improving their instruction-following and deductive reasoning abilities, leaving open the question of whether these models can truly discover new knowledge.…

Multimodal Large Language Models (MLLMs) exhibit impressive performance across various visual tasks. Subsequent investigations into enhancing their visual reasoning abilities have significantly expanded their performance envelope. However,…

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Understanding realistic visual scene images together with language descriptions is a fundamental task towards generic visual understanding. Previous works have shown compelling comprehensive results by building hierarchical structures for…