Related papers: ROVER: Recursive Reasoning Over Videos with Vision…

Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant potential in complex visual tasks through the integration of Chain-of-Thought (CoT) reasoning. However, in Video Question Answering, extended thinking…

Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale human-constructed supervision for post-training. Such supervision is costly to obtain,…

The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and describe complex visual content. However, applying these models…

Current video understanding models rely on fixed frame sampling strategies, processing predetermined visual inputs regardless of the specific reasoning requirements of each question. This static approach limits their ability to adaptively…

Interleaved reasoning paradigms enhance Multimodal Large Language Models (MLLMs) with visual feedback but are hindered by the prohibitive computational cost of re-encoding pixel-dense images. A promising alternative, latent visual…

To tackle long-horizon tasks, recent hierarchical vision-language-action (VLAs) frameworks employ vision-language model (VLM)-based planners to decompose complex manipulation tasks into simpler sub-tasks that low-level visuomotor policies…

Editing complex visual content from ambiguous or partially specified instructions remains a core challenge in vision-language modeling. Existing models can contextualize content but often fail to infer the underlying intent within a…

Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack…

Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward…

Recent advances in Vision-Language Models (VLMs) have improved performance in multi-modal learning, raising the question of whether these models truly understand the content they process. Crucially, can VLMs detect when a reasoning process…

Reinforcement Learning with Verifiable Rewards (RLVR) has substantially advanced the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, the rapid progress of MLLMs is outpacing the complexity of existing…

RL with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving the reasoning abilities of large language models (LLMs). Current methods rely primarily on policy optimization frameworks like PPO and GRPO, which follow…

Autoregressive vision-language models (VLMs) can handle many tasks within a single model, yet the representations that enable this capability remain opaque. We find that VLMs align conceptually equivalent inputs into a shared task vector,…

Legged robots are physically capable of navigating a diverse variety of environments and overcoming a wide range of obstructions. For example, in a search and rescue mission, a legged robot could climb over debris, crawl through gaps, and…

While significant research has focused on developing embodied reasoning capabilities using Vision-Language Models (VLMs) or integrating advanced VLMs into Vision-Language-Action (VLA) models for end-to-end robot control, few studies…

Multimodal Large Language Models (MLLMs) have made impressive progress in connecting vision and language, but they still struggle with spatial understanding and viewpoint-aware reasoning. Recent efforts aim to augment the input…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque;…

Multimodal Large Language Models (MLLMs) achieve strong multimodal reasoning performance, yet we identify a recurring failure mode in long-form generation: as outputs grow longer, models progressively drift away from image evidence and fall…

Reasoning about failures is crucial for building reliable and trustworthy robotic systems. Prior approaches either treat failure reasoning as a closed-set classification problem or assume access to ample human annotations. Failures in the…

Spatial reasoning has emerged as a critical capability for Multimodal Large Language Models (MLLMs), drawing increasing attention and rapid advancement. However, existing benchmarks primarily focus on single-step perception-to-judgment…