Topic: Multimodal Model

← Back to home

1. Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

   Paper • Sep 4, 2025 • arxiv.org • Qinyan Zhang, Xinping Lei, Ruijie Miao, Yu Fu, Haojie Fan, Le Chang, Jiafan Hou, Dingling Zhang, Zhongfei Hou, Ziqiang Yang, Changxin Pu, Fei Hu, Jingkai Liu, Mengyun Liu, Yang Liu, Xiang Gao, Jiaheng Liu, Tong Yang, Zaiyuan Wang, Ge Zhang, Wenhao Huang

   Large Language Models (LLMs) achieve strong performance on diverse tasks but often exhibit cognitive inertia, struggling to follow instructions that conflict with the standardized patterns learned ...

2. Robix: A Unified Model for Robot Interaction, Reasoning and Planning

   Paper • Sep 11, 2025 • arxiv.org • Huang Fang, Mengxi Zhang, Heng Dong, Wei Li, Zixuan Wang, Qifeng Zhang, Xueyun Tian, Yucheng Hu, Hang Li

   We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture. Acting as the high-level cognitive...

3. UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

   Paper • Aug 26, 2025 • arxiv.org • Zihao Huang, Yu Bao, Qiyang Min, Siyan Chen, Ran Guo, Hongzhi Huang, Defa Zhu, Yutao Zeng, Banggu Wu, Xun Zhou, Siyuan Qiao

   While Mixture of Experts (MoE) models achieve remarkable efficiency by activating only subsets of parameters, they suffer from high memory access costs during inference. Memory-layer architectures ...

4. OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

   Paper • Aug 26, 2025 • arxiv.org • Jianwen Jiang, Weihong Zeng, Zerong Zheng, Jiaqi Yang, Chao Liang, Wang Liao, Han Liang, Yuan Zhang, Mingyuan Gao

   Existing video avatar models can produce fluid human animations, yet they struggle to move beyond mere physical likeness to capture a character's authentic essence. Their motions typically synchron...

5. USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

   Paper • Aug 26, 2025 • arxiv.org • Shaojin Wu, Mengqi Huang, Yufeng Cheng, Wenxu Wu, Jiahe Tian, Yiming Luo, Fei Ding, Qian He

   Existing literature typically treats style-driven and subject-driven generation as two disjoint tasks: the former prioritizes stylistic similarity, whereas the latter insists on subject consistency...

6. AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions

   Paper • Aug 22, 2025 • arxiv.org • Zihan Wang, Jiaze Chen, Zhicheng Liu, Markus Mak, Yidi Du, Geonsik Moon, Luoqi Xu, Aaron Tua, Kunshuo Peng, Jiayi Lu, Mingfei Xia, Boqian Zou, Chenyang Ran, Guang Tian, Shoutai Zhu, Yeheng Duan, Zhenghui Kang, Zhenxing Lin, Shangshu Li, Qiang Luo, Qingshen Long, Zhiyong Chen, Yihan Xiao, Yurong Wu, Daoguang Zan, Yuyi Fu, Mingxuan Wang, Ming Ding

   Competitive programming has emerged as a critical benchmark for evaluating the reasoning and coding capabilities of Large Language Models (LLMs). Despite impressive progress on existing benchmarks,...

7. DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

   Paper • Aug 20, 2025 • arxiv.org • Shuaijie She, Yu Bao, Yu Lu, Lu Xu, Tao Li, Wenhao Zhu, Shujian Huang, Shanbo Cheng, Lu Lu, Yuxuan Wang

   We present DuPO, a dual learning-based preference optimization framework that generates annotation-free feedback via a generalized duality. DuPO addresses two key limitations: Reinforcement Learnin...

8. Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

   Paper • Aug 14, 2025 • arxiv.org • Zhipeng Chen, Xiaobo Qin, Youbin Wu, Yue Ling, Qinghao Ye, Wayne Xin Zhao, Guang Shi

   Reinforcement learning with verifiable rewards (RLVR), which typically adopts Pass@1 as the reward, has faced the issues in balancing exploration and exploitation, causing policies to prefer conser...

9. Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

   Paper • Aug 4, 2025 • arxiv.org • Yuxuan Song, Zheng Zhang, Cheng Luo, Pengyang Gao, Fan Xia, Hao Luo, Zheng Li, Yuehang Yang, Hongli Yu, Xingwei Qu, Yuwei Fu, Jing Su, Ge Zhang, Wenhao Huang, Mingxuan Wang, Lin Yan, Xiaoying Jia, Jingjing Liu, Wei-Ying Ma, Ya-Qin Zhang, Yonghui Wu, Hao Zhou

   We present Seed Diffusion Preview, a large-scale language model based on discrete-state diffusion, offering remarkably fast inference speed. Thanks to non-sequential, parallel generation, discrete ...

10. Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

    Paper • Aug 1, 2025 • arxiv.org • Luoxin Chen, Jinming Gu, Liankai Huang, Wenhao Huang, Zhicheng Jiang, Allan Jie, Xiaoran Jin, Xing Jin, Chenggang Li, Kaijing Ma, Cheng Ren, Jiawei Shen, Wenlei Shi, Tong Sun, He Sun, Jiahui Wang, Siran Wang, Zhihong Wang, Chenrui Wei, Shufa Wei, Yonghui Wu, Yuchen Wu, Yihang Xia, Huajian Xin, Fan Yang, Huaiyuan Ying, Hongyi Yuan, Zheng Yuan, Tianyang Zhan, Chi Zhang, Yue Zhang, Ge Zhang, Tianyun Zhao, Jianqiu Zhao, Yichi Zhou, Thomas Hanwen Zhu

    LLMs have demonstrated strong mathematical reasoning abilities by leveraging reinforcement learning with long chain-of-thought, yet they continue to struggle with theorem proving due to the lack of...

11. A Systematic Analysis of Hybrid Linear Attention

    Paper • Jul 8, 2025 • arxiv.org • Dustin Wang, Rui-Jie Zhu, Steven Abreu, Yong Shan, Taylor Kergan, Yuqi Pan, Yuhong Chou, Zheng Li, Ge Zhang, Wenhao Huang, Jason Eshraghian

    Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear models often suff...

12. CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization

    Paper • Jul 8, 2025 • arxiv.org • Zhongyuan Peng, Yifan Yao, Kaijing Ma, Shuyue Guo, Yizhe Li, Yichi Zhang, Chenchen Zhang, Yifan Zhang, Zhouliang Yu, Luming Li, Minghao Liu, Yihang Xia, Jiawei Shen, Yuchen Wu, Yixin Cao, Zhaoxiang Zhang, Wenhao Huang, Jiaheng Liu, Ge Zhang

    Translating natural language mathematical statements into formal, executable code is a fundamental challenge in automated theorem proving. While prior work has focused on generation and compilation...

13. Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

    Paper • Jun 23, 2025 • arxiv.org • Jiaming Han, Hao Chen, Yang Zhao, Hanyu Wang, Qi Zhao, Ziyan Yang, Hao He, Xiangyu Yue, Lu Jiang

    This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA...

14. ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs

    Paper • Sep 25, 2025 • arxiv.org • Jiaru Zou, Ling Yang, Jingwen Gu, Jiahao Qiu, Ke Shen, Jingrui He, Mengdi Wang

    Process Reward Models (PRMs) have recently emerged as a powerful framework for supervising intermediate reasoning steps in large language models (LLMs). Previous PRMs are primarily trained on model...

15. ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs

    Paper • Jun 18, 2025 • arxiv.org • Feng He, Zijun Chen, Xinnian Liang, Tingting Ma, Yunqi Qiu, Shuangzhi Wu, Junchi Yan

    Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought (Long CoT) reasoning have demonstrated remarkable cross-domain generalization capabilities. However, the underlyi...

16. Seedance 1.0: Exploring the Boundaries of Video Generation Models

    Paper • Jun 28, 2025 • arxiv.org • Yu Gao, Haoyuan Guo, Tuyen Hoang, Weilin Huang, Lu Jiang, Fangyuan Kong, Huixia Li, Jiashi Li, Liang Li, Xiaojie Li, Xunsong Li, Yifu Li, Shanchuan Lin, Zhijie Lin, Jiawei Liu, Shu Liu, Xiaonan Nie, Zhiwu Qing, Yuxi Ren, Li Sun, Zhi Tian, Rui Wang, Sen Wang, Guoqiang Wei, Guohong Wu, Jie Wu, Ruiqi Xia, Fei Xiao, Xuefeng Xiao, Jiangqiao Yan, Ceyuan Yang, Jianchao Yang, Runkai Yang, Tao Yang, Yihang Yang, Zilyu Ye, Xuejiao Zeng, Yan Zeng, Heng Zhang, Yang Zhao, Xiaozheng Zheng, Peihao Zhu, Jiaxin Zou, Feilong Zuo

    Notable breakthroughs in diffusion modeling have propelled rapid improvements in video generation, yet current foundational model still face critical challenges in simultaneously balancing prompt f...

17. PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

    Paper • Jun 5, 2025 • arxiv.org • Yuchen Lin, Chenguo Lin, Panwang Pan, Honglei Yan, Yiqiang Feng, Yadong Mu, Katerina Fragkiadaki

    We introduce PartCrafter, the first structured 3D generative model that jointly synthesizes multiple semantically meaningful and geometrically distinct 3D meshes from a single RGB image. Unlike exi...

18. Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning

    Paper • Sep 25, 2025 • arxiv.org • Yinjie Wang, Ling Yang, Ye Tian, Ke Shen, Mengdi Wang

    We propose CURE, a novel reinforcement learning framework with a dedicated reward design that co-evolves coding and unit test generation capabilities based on their interaction outcomes, without an...

19. DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction

    Paper • Nov 11, 2025 • arxiv.org • Yiheng Liu, Liao Qu, Huichao Zhang, Xu Wang, Yi Jiang, Yiming Gao, Hu Ye, Xian Li, Shuai Wang, Daniel K. Du, Fangmin Chen, Zehuan Yuan, Xinglong Wu

    This paper presents DetailFlow, a coarse-to-fine 1D autoregressive (AR) image generation method that models images through a novel next-detail prediction strategy. By learning a resolution-aware to...

20. Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles

    Paper • Jun 9, 2025 • arxiv.org • Jiangjie Chen, Qianyu He, Siyu Yuan, Aili Chen, Zhicheng Cai, Weinan Dai, Hongli Yu, Qiying Yu, Xuefeng Li, Jiaze Chen, Hao Zhou, Mingxuan Wang

    Large Language Models (LLMs), such as OpenAI's o1 and DeepSeek's R1, excel at advanced reasoning tasks like math and coding via Reinforcement Learning with Verifiable Rewards (RLVR), but still stru...