English
Related papers

Related papers: Play to Generalize: Learning to Reason Through Gam…

200 papers

Reinforcement learning (RL) can elicit strong reasoning in large language models (LLMs), yet most open efforts focus on math and code. We propose Reasoning Curriculum, a simple two-stage curriculum that first elicits reasoning skills in…

Artificial Intelligence · Computer Science 2025-10-31 Bo Pang , Deqian Kong , Silvio Savarese , Caiming Xiong , Yingbo Zhou

Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into desired robotic actions. Despite their…

Large language models have achieved significant reasoning improvements through reinforcement learning with verifiable rewards (RLVR). Yet as model capabilities grow, constructing high-quality reward signals becomes increasingly difficult,…

Machine Learning · Computer Science 2026-04-21 Salman Rahman , Jingyan Shen , Anna Mordvina , Hamid Palangi , Saadia Gabriel , Pavel Izmailov

Lately, researchers in artificial intelligence have been really interested in how language and vision come together, giving rise to the development of multimodal models that aim to seamlessly integrate textual and visual information.…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Rajat Chawla , Arkajit Datta , Tushar Verma , Adarsh Jha , Anmol Gautam , Ayush Vatsal , Sukrit Chaterjee , Mukunda NS , Ishaan Bhola

Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Haozhan Shen , Peng Liu , Jingcheng Li , Chunxin Fang , Yibo Ma , Jiajia Liao , Qiaoli Shen , Zilun Zhang , Kangjia Zhao , Qianqian Zhang , Ruochen Xu , Tiancheng Zhao

Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation capabilities. However, more modalities bring more vulnerabilities to being utilized for jailbreak…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Shiji Zhao , Shukun Xiong , Yao Huang , Yan Jin , Zhenyu Wu , Jiyang Guan , Ranjie Duan , Jialing Tao , Hui Xue , Xingxing Wei

Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Angen Ye , Zeyu Zhang , Boyuan Wang , Xiaofeng Wang , Dapeng Zhang , Zheng Zhu

Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Jiaao Yu , Shenwei Li , Mingjie Han , Yifei Yin , Wenzheng Song , Chenghao Jia , Man Lan

Accurate chart comprehension represents a critical challenge in advancing multimodal learning systems, as extensive information is compressed into structured visual representations. However, existing vision-language models (VLMs) frequently…

Machine Learning · Computer Science 2026-03-10 Xin Zhang , Xingyu Li , Rongguang Wang , Ruizhong Miao , Zheng Wang , Dan Roth , Chenyang Li

Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the reasoning capability of Multimodal Large Language Models (MLLMs) through Reinforcement…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Chaoyang Wang , Zeyu Zhang , Meng Meng , Xu Zhou , Haiyun Jiang

DeepSeek-R1-Zero has successfully demonstrated the emergence of reasoning capabilities in LLMs purely through Reinforcement Learning (RL). Inspired by this breakthrough, we explore how RL can be utilized to enhance the reasoning capability…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Wenxuan Huang , Bohan Jia , Zijie Zhai , Shaosheng Cao , Zheyu Ye , Fei Zhao , Zhe Xu , Xu Tang , Yao Hu , Shaohui Lin

In recent years, large language models (LLMs) have shown significant advancements in natural language processing (NLP), with strong capa-bilities in generation, comprehension, and rea-soning. These models have found applications in…

Artificial Intelligence · Computer Science 2025-04-02 Hui Wang

Exploration remains a key bottleneck for reinforcement learning (RL) post-training of large language models (LLMs), where sparse feedback and large action spaces can lead to premature collapse into repetitive behaviors. We propose…

Machine Learning · Computer Science 2026-02-20 Zhicheng Zhang , Ziyan Wang , Yali Du , Fei Fang

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Aarti Ghatkesar , Ganesh Venkatesh

Reinforcement learning (RL) has emerged as an effective paradigm for improving the reasoning capability of vision-language models (VLMs). However, RL-based optimization typically depends on costly high-quality annotations that are difficult…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Lin Qiu , Hanqing Zeng , Yao Liu , Bingjun Sun , Guangdeng Liao , Ji Liu

Enhancing the multimodal reasoning capabilities of Multimodal Large Language Models (MLLMs) is a challenging task that has attracted increasing attention in the community. Recently, several studies have applied Reinforcement Learning with…

Machine Learning · Computer Science 2026-03-04 Tong Xiao , Xin Xu , Zhenya Huang , Hongyu Gao , Quan Liu , Qi Liu , Enhong Chen

Robots trained via Reinforcement Learning (RL) or Imitation Learning (IL) often adapt slowly to new tasks, whereas recent Large Language Models (LLMs) and Vision-Language Models (VLMs) promise knowledge-rich planning from minimal data.…

Multimodal large language models (MLLMs) have emerged as powerful tools for visual question answering (VQA), enabling reasoning and contextual understanding across visual and textual modalities. Despite their advancements, the evaluation of…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Nikitha SR

Multi-agent reinforcement learning (MARL) provides an efficient way for simultaneously learning policies for multiple agents interacting with each other. However, in scenarios requiring complex interactions, existing algorithms can suffer…

Machine Learning · Computer Science 2022-03-08 Xiaobai Ma , David Isele , Jayesh K. Gupta , Kikuo Fujimura , Mykel J. Kochenderfer

Multimodal Large Language Models (MLLMs) have shown promising capabilities in mathematical reasoning within visual contexts across various datasets. However, most existing multimodal math benchmarks are limited to single-visual contexts,…

Artificial Intelligence · Computer Science 2025-08-04 Peijie Wang , Zhong-Zhi Li , Fei Yin , Xin Yang , Dekang Ran , Cheng-Lin Liu