Related papers: EchoInk-R1: Exploring Audio-Visual Reasoning in Mu…

Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations…

Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks successfully. Despite the success of large language models and vision language models based…

Multimodal Large Language Models (MLLM) are primarily pre-trained on the RGB modality, thereby limiting their performance on other modalities, such as infrared, depth, and event data, which are crucial for complex scenarios. To address…

Can Multimodal Large Language Models (MLLMs) discern confused objects that are visually present but audio-absent? To study this, we introduce a new benchmark, AV-ConfuseBench, which simulates an ``Audio-Visual Confusion'' scene by modifying…

Reinforcement learning has recently improved the reasoning ability of Large Language Models and Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness and consequently tolerate process hallucinations--cases where…

While large audio-language models (LALMs) have demonstrated state-of-the-art audio understanding, their reasoning capability in complex soundscapes still falls behind large vision-language models (LVLMs). Compared to the visual domain, one…

While Reinforcement Learning with Verifiable Reward (RLVR) significantly advances image reasoning in Large Vision-Language Models (LVLMs), its application to complex video reasoning remains underdeveloped. This gap stems primarily from a…

We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the…

Despite significant advancements, current large language models (LLMs) and vision-language models (LVLMs) continue to struggle with complex, multi-step, cross-modal common sense reasoning tasks, often exhibiting a lack of "deliberative…

Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that…

Large language models (LLMs) have recently shown strong reasoning abilities in domains like mathematics, coding, and scientific problem-solving, yet their potential for ranking tasks, where prime examples include retrieval, recommender…

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

Large language models (LLMs) have demonstrated strong capabilities in language understanding and reasoning, yet they remain limited when tackling real-world tasks that require up-to-date knowledge, precise operations, or specialized tool…

Recent advances in vision-language models (VLMs) have demonstrated strong generalization in natural image tasks. However, their performance often degrades on unmanned aerial vehicle (UAV)-based aerial imagery, which features high…

Recently, improving the reasoning ability of large multimodal models (LMMs) through reinforcement learning has made great progress. However, most existing works are based on highly reasoning-intensive datasets such as mathematics and code,…

We propose Rec-R1, a general reinforcement learning framework that bridges large language models (LLMs) with recommendation systems through closed-loop optimization. Unlike prompting and supervised fine-tuning (SFT), Rec-R1 directly…

DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs). While recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings, they face limitations, including inconsistencies…

Recent breakthroughs in reasoning language models have significantly advanced text-based reasoning. On the other hand, Multi-modal Large Language Models (MLLMs) still lag behind, hindered by their outdated internal LLMs. Upgrading these…

Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy…

Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR approaches typically rely on outcome-driven optimization that…