相关论文: Structured Preference Optimization for Vision-Lang…

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with…

Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals although they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop…

Recent advances in large vision-language models (LVLMs) have shown promise for embodied task planning, yet they struggle with fundamental challenges like dependency constraints and efficiency. Existing approaches either solely optimize…

Current Vision-Language Models (VLMs) struggle with fine-grained spatial reasoning, particularly when multi-step logic and precise spatial alignment are required. In this work, we introduce SpatialReasoner-R1, a vision-language reasoning…

Well-designed prompts are crucial for enhancing Large language models' (LLMs) reasoning capabilities while aligning their outputs with task requirements across diverse domains. However, manually designed prompts require expertise and…

Multimodal Large Language Models (MLLMs) have significantly improved the performance of various tasks, but continue to suffer from visual hallucinations, a critical issue where generated responses contradict visual evidence. While Direct…

Online and offline RLHF methods, such as PPO and DPO, have been highly successful in aligning AI with human preferences. Despite their success, however, these methods suffer from fundamental limitations: (a) Models trained with RLHF can…

Despite advances in pretraining with extended context lengths, large language models (LLMs) still face challenges in effectively utilizing real-world long-context information, primarily due to insufficient long-context alignment caused by…

Enhancing the reasoning capabilities of large language models effectively using reinforcement learning (RL) remains a crucial challenge. Existing approaches primarily adopt two contrasting advantage estimation granularities: token-level…

Direct Preference Optimization (DPO) has gained significant attention for its simplicity and computational efficiency in aligning large language models (LLMs). Recent advancements have extended DPO to multimodal scenarios, achieving strong…

Reinforcement Learning with Human Feedback (RLHF) enhances the alignment of Large Language Models (LLMs). However, its limitations have led to the development of Direct Preference Optimization (DPO), an RL-free approach designed to overcome…

Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit…

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…

Test-time scaling has proven effective in further enhancing the performance of pretrained Large Language Models (LLMs). However, mainstream post-training methods (i.e., reinforcement learning (RL) with chain-of-thought (CoT) reasoning)…

Enhancing the conformity of large language models (LLMs) to human preferences remains an ongoing research challenge. Recently, offline approaches such as Direct Preference Optimization (DPO) have gained prominence as attractive options due…

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…

Supervised Fine-Tuning (SFT) has been a go-to and effective method for enhancing long chain-of-thought (CoT) reasoning in relatively small LLMs by fine-tuning them with long CoT responses from larger LLMs. To continually improve reasoning…

Large Vision-Language Models (LVLMs) hold immense potential for complex multimodal instruction following, yet their development is often hindered by the high cost and inconsistency of human annotation required for effective fine-tuning and…

Recent alignment methods based on Direct Preference Optimization (DPO) reformulate preference learning as supervised optimization over pairwise comparisons, offering improved efficiency and stability over reinforcement learning from human…