相关论文: SATORI-R1: Incentivizing Multimodal Reasoning thro…

Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward models to produce explicit, multi-dimensional critiques…

Reinforcement learning has proven its effectiveness in enhancing the reasoning capabilities of large language models. Recent research efforts have progressively extended this paradigm to multimodal reasoning tasks. Due to the inherent…

This paper addresses the critical and underexplored challenge of long video understanding with low computational budgets. We propose LongVideo-R1, an active, reasoning-equipped multimodal large language model (MLLM) agent designed for…

The growing prevalence of tampered images poses serious security threats, highlighting the urgent need for reliable detection methods. Multimodal large language models (MLLMs) demonstrate strong potential in analyzing tampered images and…

Reference Audio-Visual Segmentation (Ref-AVS) tasks challenge models to precisely locate sounding objects by integrating visual, auditory, and textual cues. Existing methods often lack genuine semantic understanding, tending to memorize…

Traditional visual grounding methods primarily focus on single-image scenarios with simple textual references. However, extending these methods to real-world scenarios that involve implicit and complex instructions, particularly in…

Large vision-language models (VLMs) have made significant strides in 2D visual understanding tasks, sparking interest in extending these capabilities to 3D scene understanding. However, current 3D VLMs often struggle with robust reasoning…

Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able to synthesize vision-centric problems spanning diverse levels…

Vision-based reinforcement learning (RL) is a promising technique to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Group relative policy optimization (GRPO) has become a standard post-training paradigm for improving reasoning and preference alignment in large language models (LLMs), and has recently shown strong effectiveness in LLM-based recommender…

The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs). While DeepSeek-R1 and other follow-up work primarily focus…

Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and natural language goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle with the…

Visual reasoning tasks such as visual question answering (VQA) require an interplay of visual perception with reasoning about the question semantics grounded in perception. However, recent advances in this area are still primarily driven by…

Recent large vision-language models (LVLMs) have demonstrated impressive reasoning ability by generating long chain-of-thought (CoT) responses. However, CoT reasoning in multimodal contexts is highly vulnerable to visual hallucination…

Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models…

Training language models to produce both correct answers and sound reasoning remains an open challenge. Reinforcement learning with verifiable rewards typically optimizes only final outcomes, which can lead to a failure mode where task…

Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct answering remain underexplored. In this paper, we first…

Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer…

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet how visual evidence is integrated during reasoning remains poorly understood. We…

Since its inception, Visual Question Answering (VQA) is notoriously known as a task, where models are prone to exploit biases in datasets to find shortcuts instead of performing high-level reasoning. Classical methods address this by…