📄 Notable* Recent AI/ML arXiv Papers

Last updated just now...

📄 Latent Lattice Language Models
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.21608v1
👥 Authors: Shivam Duggal, Zongze Wu, William T. Freeman (possible past Massachusetts Institute Of Technology affiliation), Antonio Torralba (possible past Massachusetts Institute Of Technology affiliation), Richard Zhang, Eli Shechtman
Abstract

Language models typically increase per-token computation through deeper or looped layers and latent reasoning steps, while richer residual connections improve information flow across layers. We instead increase computational capacity: the number of active computational states a model maintains. We introduce the Lattice of Latents, a set of per-layer horizontal latent streams that run recurrently along time, alongside the vertical residual stream that flows through depth. Like hyper-connections, ...

📄 Learning to Reason with Predictive Gains for Generative Recommendation
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.21441v1
👥 Authors: Zhuoyang Li, Teng Shi, Jiakai Tang, Weijie Yu, Guofu Xie, Xiao Zhang (possible past Tsinghua University affiliation), Lei Kou, Yang Yu, Lei Shen, Xin Chen (possible past Tencent (China) affiliation), Bing Wang, Xiaoyi Zeng, Jun Xu (possible past Google (United States) affiliation)
Abstract

Reasoning-enhanced generative recommendation (GR) has attracted increasing attention for leveraging the reasoning capabilities of large language models (LLMs) to improve next-item prediction. However, existing methods primarily optimize reasoning through Group Relative Policy Optimization (GRPO) with rule-based rewards determined by final recommendation performance, which faces two key limitations: (i) unmeasured predictive contributions within reasoning, where the predictive contributions of in...

📄 WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.21373v1
👥 Authors: Yipeng Du, Yuxi Li, Ying Zhang (possible past Tencent (China) affiliation), Chong Sun (possible past Tencent (China) affiliation), Chen Li (possible past Tencent (China) affiliation), Jing Lyu, Ying Tai (possible past Tencent (China) affiliation)
Abstract

Recent advances in video generation call for reliable detection grounded in explicit forensic evidence. However, current methods primarily depend on single-pass chain-of-thought reasoning that overlooks brief or localized artifacts, or on predefined multi-agent workflows that offer limited flexibility in selecting relevant inspections. Even with adaptive investigation, optimizing the investigation policy alone does not directly improve the forensic capabilities of fixed experts. We introduce WeV...

📄 Turing Agent: Agentic Formal Verification for Mathematical Research
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.21299v1
👥 Authors: Yang Chen (possible past Tencent (China) affiliation), Qianyi Wang, Ronghui Yang, Zhanhao Li, Yu Cong, Chen Zhang (possible past Peking University affiliation), Hangfan Zhang, Shao Zhang, Shuai Li, Toru Takisaka, Chao Xu, Yi Zhou, Zhihao Tang, Xiao Wang (possible past Google (United States) affiliation), Bo Zhang (possible past Tencent (China) affiliation), Shuyue Hu
Abstract

Large language models (LLMs) are rapidly advancing mathematical discovery, moving beyond benchmark-level problem solving to tackle frontier research problems. This progress is ushering mathematics into an era of proof abundance, raising a fundamental challenge: how can we ensure the correctness of the ever-growing volume of AI-generated proofs and transform them into trustworthy, machine-verified mathematical knowledge? We introduce Turing Agent, an agent harness designed to orchestrate end-to-e...

📄 Sage S2.1 Flash Technical Report
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.21072v1
👥 Authors: Kun Cai, Haodong Chen, Guangran Cheng, Qingxiu Cheng, Xu Dai, Guanting Dong, Qiming Ge, Lixin Gu, Tao Gui, Honglin Guo, Yuyang Hu, Zixian Huang, Jiajie Jin, Alexander Lam, Jiaqiang Li, Yining Li, Jiahang Lin, Yanjiang Liu, Xinyu Lu, Haijun Lv (possible past Baidu (China) affiliation), Ningsheng Ma, Zerun Ma, Minlong Peng, Jianmin Qian, Huayu Sha, Junlin Shang, Shuo Shen, Qisheng Su, Jiajun Sun, Yanan Sun (possible past Tencent (China) affiliation), Zhichao Sun, Ran Tao, Zhongbo Tian, Guoqiang Wang, Hui Wang, Rui Wang (possible past Tencent (China) affiliation), Yiding Wang, Zhecan Wang, Hao Xiang, Xinchen Xie, Shuhao Xing, Xiaoyu Xing, Wanghan Xu, Xinyu Yang, Yajie Yang, Dingbo Yuan, Yuhang Zang, Hongjie Zhang, Chengfeng Zhao, Haoran Zhao, Penghao Zhao, Ruojun Zhou, Dongsheng Zhu, Yicheng Zou, Qiye Cai, Yifei Cao, Xinmeng Che, Hongji Chen, Jiabei Chen, Jiadong Chen, Jiahao Chen, Jiayi Chen, Xinjie Chen, Yujia Chen, Xin Deng, Yi Dong, Yichen Dong, Wenjie Fu, Jianing Geng, Chenyang Gu, Ding Han, Han Han, Feiyang Hao, Haotan He, Qiushi He, Xufeng He, Xin Hong, Jie Hou, Binze Hu, Yongkang Hu, Zijian Hu, Enfu Huang, Junhao Huang, Changhao Jiang, Huicheng Jiang, Jiazhen Jiang, Shufan Jiang, Wenqing Jing, Jiahao Kuang, Bowen Lai, Bo Li (possible past Tencent (China) affiliation), Qi Li, Qilong Li, Zhuoqun Li, Tianhao Liang, Jiaxiang Liu, Junzhang Liu, Shaofan Liu, Shuainan Liu, Tong Liu, Yi Liu (possible past Google (United States) affiliation), Ziyu Liu, Zhonghang Lu, Jianwen Luo, Xuan Luo (possible past University Of Washington affiliation), Yanyi Luo, Huijie Lv, Mingyu Ma, Houcheng Min, Hongjun Mo, Songhao Ni, Chengjun Pan, Qiyuan Peng, Xiaoxuan Peng, Wanying Ren, Runhui Ruan, Jifei Shan, Zixin Shang, Bing Shao, Zhuohui Sheng, Jiayang Shi, Qingyun Shi, Yang Shu, Aierpanjiang Simayi, Sirui Song, Yuxiao Song, Jiahao Sun, Zhe Sun (possible past Tsinghua University affiliation), Wenzhe Tan, Guoxiang Wang, Hanchen Wang (possible past University Of Cambridge affiliation), Jie Wang (possible past Tsinghua University affiliation), Pengbo Wang, Qing Wang, Rui Wang (possible past Tencent (China) affiliation), Weihang Wang, Xiaotao Wang, Yuhui Wang, Zhekai Wang, Zihan Wang (possible past Tsinghua University affiliation), Zile Wang, Jinke Wu, Liwei Wu, Xuansheng Wu, Yida Wu, Yihao Wu, Yinqi Wu, Yue Wu, Yuhan Wu, Yuwa Wu, Zhiheng Xi, Ying Xiao (possible past Google (United States) affiliation), Zhide Xie, Caijun Xu, Xingle Xu, Yichen Xu, Yongfeng Xu, Xiaolei Yang, Zhixiong Yang, Jiacheng Yao, Dingcheng Yi, Shihong Yi, Jinhui Yin, Peizhou Yu, Shan Yu, Hao Yuan, Junjie Yuan, Xiongyao Zha, Bo Zhang (possible past Tencent (China) affiliation), Caixian Zhang, Kaicheng Zhang, Pengxiang Zhang, Qiuyinzhe Zhang, Wei Zhang (possible past Tsinghua University affiliation), Xiaoqian Zhang, Xinsen Zhang, Jiyuan Zhao, Shuyu Zhao, Pujun Zheng, Zheyu Zheng, Xiaoxue Zhong, Peiheng Zhou, Xiaohao Zhou, Xinyu Zhou, Fangyi Zhu, Guanru Zhu, Yulun Zhu, Jiabao Zhuang, Pengfei Cao, Zhicheng Dou, Xianpei Han (possible past Tencent (China) affiliation), Ben He, Guoxiu He, Xuanjing Huang, Tao Ji, Yu-Gang Jiang, Dahua Lin, Hongyu Lin, Kang Liu, Yaojie Lu, Le Sun, Ji-Rong Wen, Jun Zhao, Yutao Zhu, Qi Zhang (possible past Tencent (China) affiliation), Bowen Zhou
Abstract

We introduce Sage S1.5 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents spectra as ordered patches of measurements. Modality-specific projectors map these representations into the input space of a shared backbone, which processes them alongside text and images. To develop the model's agent ...

📄 SWE-OPD: On-Policy Distillation for Agentic Coding
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.21020v1
👥 Authors: Yuhang He, Yanyu Chen, Chuanzhe Guo, Jie Zhu, Zichen Tian, Hongyu Ge, Zixuan Ren, Huang He, Bingjin Chen, Junyuan Shang, Shuohuan Wang (possible past Baidu (China) affiliation), Yongqi Zhang, Irwin King, Jing Liu (possible past Baidu (China) affiliation)
Abstract

In this work, we study on-policy distillation (OPD) for transferring agentic coding capabilities from a large teacher model to a smaller student model. Prior work has focused primarily on reasoning and short-horizon agentic tasks. We present SWE-OPD, a minimal OPD study for software engineering, where the student interacts with executable repositories and the teacher supervises the prefixes visited by the student. Across three teacher--student pairs, two training sources, and three SWE benchmark...

📄 K2-Horizon: A Frontier Fleet of Open Source Language Models
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.21003v1
👥 Authors: K2 Team, Zhengzhong Liu (possible past Tencent (China) affiliation), Haonan Li, Xuezhe Ma (possible past Carnegie Mellon University affiliation), Alexander Moreno, Subham Sekhar Sahoo, Rupesh Kumar Srivastava, Mikhail Yurochkin, Hadi Abdine, Yash Akhauri, Adharsh Babu, David Bellamy, Jalaj Bhandari, Dani Bouch, Wail Bouhedja, Weili Cao, Ahmad Chamma, Po-Chun Chang, Junlin Chen, Lingjie Chen, Zhoujun Cheng, Kyle Chickering, Ryandito Diandaru, Evan Dufraisse, Chaitanya Dwivedi, Bilal El Bouardi, Desai Fan, Richard Fan, Chengqian Gao, Rifo Ahmad Genadi, Jonathan Geuter, Charles Guille-Escuret, Willis Guo, Dhawal Gupta, Seungwook Han, Tingxu Han, Shibo Hao, Besher Hassan, Guowei He, Ming Shan Hee, Joel Hestness, Yu Huang (possible past Tencent (China) affiliation), Yuan Huang, Haolong Jia, Linghao Jin, Junu Kim, Lingjing Kong, Nurkhan Laiyk, Andrej Leban, Liqun Ma, John Maggs, Amr Mohamed, Mukhesh Narra, Omkar Pangarkar, Aldo Pareja, Khiem Pham, Varad Pimpalkhute, Nikhil Ranjan, Elizaveta Rebrova, Hector Ren, Shaurya Rohatgi, Guokan Shang, Jianshu She, Chufan Shi, Aaryamonvikram Singh, Daria Soboleva, Kartik Sreenivasan, Suqi Sun, Yuekai Sun, Bowen Tan, Liping Tang, Shengkun Tang, Muzi Tao, Mallikarjuna Tupakula, Micah Villmow, Hongyi Wang, Huijuan Wang, Renxi Wang, Yongxin Wang, Yuqi Wang, Zhenting Wang, Shicheng Wen, Yingquan Wu, Anze Xie, Andrew Xing, Matthew Yang, Shuanghai Yu, Kerem Zaman, Zenan Zhai, Hongli Zhan, Xuezhou Zhang, Anshun Asher Zheng, Zhe Zhou, Richard Zhuang, Eric P. Xing
Abstract

We present K2-Horizon, a fleet of six fully open language models, from a 0.9B dense model to a 375B-A23B MoE, built for general-purpose reasoning and agentic work across math and science, software engineering, deep research, office automation, and beyond. The models lead or are competitive with strong open models of their size on agentic and coding benchmarks. On the modeling side, to strengthen reasoning, we introduce Mixture-of-Value Attention (MoVA), applying MoE to attention value projection...

📄 From Recursion to Convolution: Parallel Self-Improvement for Multi-Agent Systems
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.20891v1
👥 Authors: Zheng Wang, Yuang Liu, Sachith Abeywickrama, Yangkai Ding, Tao Yu (possible past University Of Washington affiliation), Xinyu Zhang (possible past Baidu (China) affiliation), Hongbo Wang, Qi Ye, Xuefeng Jin, Zhangchun Zhao
Abstract

Multi-agent self-improvement enables agents to improve through interaction and feedback. However, sequential dependencies across agents and refinement rounds can propagate errors, increase computational costs, and limit parallelism. Moreover, refining individual features or agents in isolation can overlook their dependencies and restrict collective coordination. To address these challenges, we propose ConvRSI, a framework for parallelizing multi-agent self-improvement through convolution. ConvRS...

📄 Regularizing Treatment Leakage for LLM-based Uplift Estimation
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.20794v1
👥 Authors: Bojing Feng, Jinqiu Deng, Zihan Hong, Yuan Xue (possible past Google (United States) affiliation), Wenqi Xiang, Shuhan Wang, Feng Xiao (possible past Google (United States) affiliation), Shiwei Wang, Zijiang Liu, Shaomin Li, Yongzhi Qi
Abstract

Uplift modeling estimates the conditional average treatment effect (CATE) and supports industrial decisions such as promotional pricing. When large language models (LLMs) encode product text, treatment-revealing content can introduce shortcuts that do not transfer to deployment. We propose \emph{LLM-based Uplift Leakage Regularization} (\textsc{LULR}), which uses a CLUB-based penalty on the causal head's trainable shared representation while keeping the LLM encoder frozen. Controlled proxy exper...

📄 Nemotron 3.5 Bolt E4B 4GB: An Open and Efficient Small Language Model for Fast Conversational Agents
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.20771v1
👥 Authors: Nvidia, :, Adi Margolin, Aditya Malte, Aishwarya Chhabra, Alex Hodson, Ameya Sunil Mahabaleshwarkar, Ambrish Dantrey, Amy Shen, Andrii Skliar, Annamalai Chockalingam, Anusha Pant, Ashwath Aithal, Ashwin Kumar, Besmira Nushi, Bhavesh Pawar, Bryan Catanzaro (possible past University Of California, Berkeley affiliation), Bryan Yu, Chantal Hwang, Chenhan Yu, Chris Alexiuk, Conner Currie, Cynthia Gao (possible past Meta (United States) affiliation), David Mosallanezhad, Dina Yared, Ehsan Hosseini Asl, Eileen Long, Erick Galinkin, Felix Friedmann, Giedrius Burachas, Gorkem Batmaz, Grzegorz Chlebus, Guillermo Siman, Haifeng Qian, Hao Guo, Hayley Ross, Hrishith Thadicherla, Hui Wang, Huiying Li, Ike Nnoli, Irina Filatova, Iris Liu, Ji-Eun Lee, Jian Leong (possible past University Of California, Berkeley affiliation), Jian Zhang (possible past Tencent (China) affiliation), Jiaqi Zeng, Joey Conway, Jonathan Cohen (possible past Nvidia (United States) affiliation), Jose Vergara, Julien Veron Vialard, Kari Briski, Katherine Luna, Kedar Pandurang Potdar, Kevin Ning, Khalil Ben Khaled, Krzysztof Pawelec, Laura Dykes, Leili Tavabi, Lily Lee, Linda Liu, Liwei Ding, Maka Dong, Manoj Kilaru, Maria Bagdasarova, Matthew Lee, Meredith Price, Micah Schaffer, Michael Boone, Michael Fukuyama, Michael Hasper, Nancy Agarwal, Negar Habibi, Oleksii Kuchaiev (possible past Nvidia (United States) affiliation), Oluwatobi Olabiyi, Pablo Ribalta (possible past Nvidia (United States) affiliation), Payal Motwani, Pinky Xu, Prasoon Varshney, Pritam Biswas, Puhui Meng, Rameshwar Shivbhakta, Ran Zilberstein, Reka Kovacs, Richard Mazzarese, Rishabh Garg, Rita Fernandes Neves, Rochelle Woods, Ruby Ye, Ruvaid Virk, Ryan Hill, Saeid Motiian, Seph Mard, Shai Ben Nun, Shaona Ghosh, Sharad Yadav, Sudeep Sabnis, Suhas Hariharapura Sheshadri, Terry Kong, Thanh Do, Thinh Le, Udi Karpas, Viet Anh Trinh, Vinay Raman, Vinita Sharma, Warren Drones, Wenwen Gao, Whei Hsueh, Will Efstratis, Yoshi Suhara, Yunsheng Liu, Zhenming Wang, Zijia Chen, Zuhair Ahmed
Abstract

We introduce Nemotron 3.5 Bolt E4B 4GB, an open and efficient small language model further post-trained from Gemma-4-E4B-it and optimized for speed and intelligence per GB of memory used for fast conversational agents. The model carries forward Gemma's strong conversational capabilities and further improves multi-turn tool use, instruction following, and input grounding for fast, local voice/device assistants, interactive personas, and embedded/Edge interfaces. The model combines natural convers...

📄 VAHBench: A Harness Benchmark for Agentic Long-Video Generation
🗓️ Published: 11/16/2026
🔗 http://arxiv.org/abs/2611.20535v1
👥 Authors: Hongbo Zhang, Liuyang Song, Hang Zhou (possible past Baidu (China) affiliation), Xinchen Liu, Wei He (possible past Baidu (China) affiliation), Kai Han, Yunhe Wang
Abstract

AI agents are commonly used for everyday information retrieval and coding. We ask whether they can also interpret human requests and turn them into complete videos. We introduce VAHBench, a benchmark that tests this ability through five short-drama briefs specifying story, characters, dialogue and duration. Agents plan and carry out production using shared generation tools. Evaluation combines video completeness and basic quality with checks of production reliability and reporting accuracy. Acro...

*Notable papers are those with at least two authors from a "big" AI/ML lab.