Related papers: Visual-ERM: Reward Modeling for Visual Equivalence

Existing Vision-Language Models often struggle with complex, multi-question reasoning tasks where partial correctness is crucial for effective learning. Traditional reward mechanisms, which provide a single binary score for an entire…

Reward models play an essential role in training vision-language models (VLMs) by assessing output quality to enable aligning with human preferences. Despite their importance, the research community lacks comprehensive open benchmarks for…

Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, which hinders their usage in high-stakes domains. Existing verbalized confidence…

Advances in large reasoning models have shown strong performance on complex reasoning tasks by scaling test-time compute through extended reasoning. However, recent studies observe that in vision-dependent tasks, extended textual reasoning…

Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM) converts the…

Recent advances in vision-language models (VLMs) have significantly improved performance in embodied tasks such as goal decomposition and visual comprehension. However, providing accurate rewards for robotic manipulation without fine-tuning…

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two…

Reward engineering, the manual specification of reward functions to induce desired agent behavior, remains a fundamental challenge in multi-agent reinforcement learning. This difficulty is amplified by credit assignment ambiguity,…

Reward design remains a critical bottleneck in visual reinforcement learning (RL) for robotic manipulation. In simulated environments, rewards are conventionally designed based on the distance to a target position. However, such precise…

Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies…

Cross-modal entity linking refers to the ability to align entities and their attributes across different modalities. While cross-modal entity linking is a fundamental skill needed for real-world applications such as multimodal code…

Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a…

The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs)…

The advancement of large language models (LLMs) has significantly broadened the scope of applications in natural language processing, with multi-modal LLMs extending these capabilities to integrate and interpret visual data. However,…

Large Vision-Language Models (LVLMs) have achieved remarkable success, yet their significant computational demands hinder practical deployment. While efforts to improve LVLM efficiency are growing, existing methods lack comprehensive…

Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks…

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) alignment requires fundamentally different approaches remains unclear. Given the…

Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel…