相关论文: RationalRewards: Reasoning Rewards Scale Visual Ge…

Recent advances in multimodal reward modeling have been largely driven by a paradigm shift from discriminative to generative approaches. Building on this progress, recent studies have further employed reinforcement learning from verifiable…

Reinforcement Learning with Verifiable Rewards~(RLVR) has emerged as a powerful learn-to-reason paradigm for large reasoning models to tackle complex tasks. However, the current RLVR paradigm is still not efficient enough, as it works in a…

We introduce MotionRL, the first approach to utilize Multi-Reward Reinforcement Learning (RL) for optimizing text-to-motion generation tasks and aligning them with human preferences. Previous works focused on improving numerical performance…

Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting…

Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training…

Visual reasoning abilities play a crucial role in understanding complex multimodal data, advancing both domain-specific applications and artificial general intelligence (AGI). Existing methods enhance Vision-Language Models (VLMs) through…

Reinforcement learning with verifiable rewards helps reasoning, but GRPO-style methods stall on hard prompts where all sampled rollouts fail. SORT adds a repair update for those failures without changing rollout generation: it derives a…

Recent advancements in improving the reasoning capabilities of Large Language Models have underscored the efficacy of Process Reward Models (PRMs) in addressing intermediate errors through structured feedback mechanisms. This study analyzes…

The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning from flawed logic. Prior work generally assumes that…

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to achieve remarkable reasoning in domains like mathematics and coding, where verifiable rewards provide clear signals. However, extending this paradigm to financial…

The capabilities of Large Vision-Language Models (LVLMs) have reached state-of-the-art on many visual reasoning tasks, including chart reasoning, yet they still falter on out-of-distribution (OOD) data, and degrade further when asked to…

Recent advances in large language models (LLMs) have significantly improved performance on the Text-to-SQL task by leveraging their powerful reasoning capabilities. To enhance accuracy during the reasoning process, external Process Reward…

As a typical open-ended generation task, creative writing lacks verifiable reference answers, which has long constrained reward modeling and automatic evaluation due to high human annotation costs, evaluative bias, and coarse feedback…

Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior work has attempted to enhance prompts using large language…

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified.…

Physical reasoning over visual inputs demands tight integration of visual perception, domain knowledge, and multi-step symbolic inference. Yet even state-of-the-art Vision Language Models (VLMs) fall far short of human performance on…

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for enhancing the reasoning capabilities of large language models (LLMs). In this context, models explore reasoning trajectories and exploit rollouts…

In vision-language modeling, critic models are typically trained to evaluate outputs -- assigning scalar scores or pairwise preferences -- rather than to generate responses. This separation from policy models, which produce the responses,…

Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from human feedback has been successful in aligning agents with…

Recent advances in large video-language models (VLMs) rely on extensive fine-tuning techniques that strengthen alignment between textual and visual comprehension. Leading pipelines typically pair supervised fine-tuning (SFT) with…