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

While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-centric paradigm, limiting their applicability to complex visual…

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…

Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or…

Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning…

Vision-language models (VLMs) mainly rely on contrastive training to learn general-purpose representations of images and captions. We focus on the situation when one image is associated with several captions, each caption containing both…

Teaching large language models (LLMs) to be faithful in the provided context is crucial for building reliable information-seeking systems. Therefore, we propose a systematic framework, CANOE, to reduce faithfulness hallucinations of LLMs…

Scaling vision-language-action (VLA) model pre-training requires large volumes of diverse, high-quality manipulation trajectories. Most current data is obtained via human teleoperation, which is expensive and difficult to scale.…

Despite the success of Large Vision--Language Models (LVLMs), most existing architectures suffer from a representation bottleneck: they rely on static, instruction-agnostic vision encoders whose visual representations are utilized in an…

Next-token prediction is the fundamental principle for training large language models (LLMs), and reinforcement learning (RL) further enhances their reasoning performance. As an effective way to model language, image, video, and other…

Cross-domain task-oriented dialogue requires reasoning over implicit and explicit feasibility constraints while planning long-horizon, multi-turn actions. Large language models (LLMs) can infer such constraints but are unreliable over long…

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning…

Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language models (LLMs) in domains such as mathematics and coding. However, its applications on…

The emergence of vision language models (VLMs) bridges the gap between vision and language, enabling multimodal understanding beyond traditional visual-only deep learning models. However, transferring VLMs from the natural image domain to…

Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs). Particularly, the "Zero" reinforcement learning introduced by Deepseek-R1-Zero, enables direct…

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training method for improving the reasoning abilities of Large Language Models (LLMs). However, existing methods mainly apply uniform optimization…

Designing effective reward functions remains a major challenge in reinforcement learning (RL), often requiring considerable human expertise and iterative refinement. Recent advances leverage Large Language Models (LLMs) for automated reward…

Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision…

Lately, researchers in artificial intelligence have been really interested in how language and vision come together, giving rise to the development of multimodal models that aim to seamlessly integrate textual and visual information.…

Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This…

The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle…