相关论文: Regulating Anatomy-Aware Rewards via Trajectory-In…

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…

Foundation diffusion models can generate photorealistic natural images, but adapting them to medical imaging remains challenging. In medical adaptation, limited labeled data can exacerbate hallucination-like and clinically implausible…

Recent advances in reinforcement learning from human feedback (RLHF) and preference optimization have substantially improved the usability, coherence, and safety of large language models. However, recurring behaviors such as performative…

Multimodal large language models (MLLMs) have recently shown strong performance in visual understanding, yet they often lack temporal awareness, particularly in egocentric settings where reasoning depends on the correct ordering and…

In recent years, reinforcement learning (RL)-based methods for learning driving policies have gained increasing attention in the autonomous driving community and have achieved remarkable progress in various driving scenarios. However,…

Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes. While recent alignment techniques such as RLHF and DPO have mitigated some of these issues, they remain…

Large multimodal reasoning models have achieved rapid progress, but their advancement is constrained by two major limitations: the absence of open, large-scale, high-quality long chain-of-thought (CoT) data, and the instability of…

Automating clinical documentation with large language models requires precise alignment with priorities such as completeness and factual grounding. We present an evaluation-integrated reinforcement learning framework for long-form clinical…

Reinforcement learning in large language models (LLMs) often relies on scalar rewards, a practice that discards valuable textual rationale buried in the rollouts, forcing the model to explore \textit{de novo} with each attempt and hindering…

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for robotic manipulation. However, existing post-training methods face a dilemma between stability and exploration: Supervised Fine-Tuning (SFT) is constrained by…

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image…

Using effective generalization capabilities of vision language models (VLMs) in context-specific dynamic tasks for embodied artificial intelligence remains a significant challenge. Although supervised fine-tuned models can better align with…

The application of Vision-Language Models (VLMs) in medicine is critically hampered by the scarcity of high-quality, expert-annotated data. Supervised Fine-Tuning (SFT) on existing datasets often leads to poor generalization on unseen…

Complex video reasoning remains a significant challenge for Multimodal Large Language Models (MLLMs), as current R1-based methodologies often prioritize text-centric reasoning derived from text-based and image-based developments. In video…

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across…

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise…

Group Relative Policy Optimization (GRPO) enhances LLM reasoning but often induces overconfidence, where incorrect responses yield lower perplexity than correct ones, degrading relative calibration as described by the Area Under the Curve…

Multimodal LLMs often produce fluent yet unreliable reasoning, exhibiting weak step-to-step coherence and insufficient visual grounding, largely because existing alignment approaches supervise only the final answer while ignoring the…

Current RLHF methods such as PPO and DPO typically reduce human preferences to binary labels, which are costly to obtain and too coarse to reflect individual variation. We observe that expressions of satisfaction and dissatisfaction follow…

Real-World Image Super-Resolution is one of the most challenging task in image restoration. However, existing methods struggle with an accurate understanding of degraded image content, leading to reconstructed results that are both…