语言大模型 / LLM

Larger Is Not Always Better: Leveraging Structured Code Diffs for Comment Inconsistency Detection

更大并不总是更好：利用结构化代码差异进行注释不一致检测

Phong Nguyen, Anh M. T. Bui, Phuong T. Nguyen

专题命中 评测与基准 ：large language model(abstract)；language model(abstract)

AI总结 本文提出基于CodeT5+的即时CCI检测方法，通过分解代码修改活动序列以更准确捕捉代码与过时注释之间的相关性，提升检测性能。

Comments This paper has been reviewed and accepted to the Short Papers and Posters Track of SANER 2026

Leveraging Lightweight Entity Extraction for Scalable Event-Based Image Retrieval

利用轻量级实体提取实现可扩展的基于事件的图像检索

Dao Sy Duy Minh, Huynh Trung Kiet, Nguyen Lam Phu Quy, Phu-Hoa Pham, Tran Chi Nguyen

机构 * University of Science - VNUHCM（越南胡志明市科学大学） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.AI

AI总结 本文提出一种轻量级两阶段检索流程，利用事件中心实体提取结合BM25和BEiT-3模型，实现高效准确的图像检索。

Comments System description paper for EVENTA Grand Challenge Track 2 at ACM Multimedia 2025 (MM '25). Ranked 4th place. 6 pages, 1 figure, 2 tables

NotSoTiny: A Large, Living Benchmark for RTL Code Generation

NotSoTiny: 一个大规模、活体的RTL代码生成基准

Razine Moundir Ghorab, Emanuele Parisi, Cristian Gutierrez, Miquel Alberti-Binimelis, Miquel Moreto, Dario Garcia-Gasulla, Gokcen Kestor

机构 * Barcelona Supercomputing Center（巴塞罗那超级计算中心） ； Universitat Politecnica de Catalunya（加泰罗尼亚理工大学） 纠错

专题命中 评测与基准 ：LLM(abstract)；分类 cs.AI

AI总结 NotSoTiny是一个大规模、活体的RTL代码生成基准，通过评估LLM生成结构丰富且具有上下文意识的RTL代码的能力，以克服当前LLM在硬件设计中的限制并推动技术发展。

Comments 9 pages, 5 figures

Gobernanza y trazabilidad "a prueba de AI Act" para casos de uso legales: un marco técnico-jurídico, métricas forenses y evidencias auditables

AI Act合规的法律用例治理与可追溯性：技术-法律框架、司法计量学与可审计证据

Alex Dantart

机构 * Humanizing Internet 纠错

专题命中 评测与基准 ：LLM(abstract)；分类 cs.AI

AI总结 本文提出一个开源框架rag-forense，用于确保AI系统在法律领域符合欧盟AI法案的可验证合规性。

Comments in Spanish and English languages

RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events

RSCC：一种大规模遥感变化描述数据集用于灾害事件

Zhenyuan Chen, Chenxi Wang, Ningyu Zhang, Feng Zhang

机构 * School of Earth Sciences, Zhejiang University（浙江大学地球科学学院） ； School of Software Technology, Zhejiang University（浙江大学软件学院） ； Zhejiang Provincial Key Laboratory of Geographic Information Science（浙江省地理信息科学重点实验室） ； Key Laboratory of Spatio-temporal Information and Intelligent Services (LSIIS), Ministry of Natural Resources of the People’s Republic of China（国家自然资源部空间时空信息与智能服务重点实验室） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.CL

AI总结 RSCC数据集通过提供大规模遥感图像对和详细变化描述，提升视觉-语言模型在灾害事件双时间理解中的性能和应用能力。

Comments Accepted by NeurIPS 2025 Dataset and Benchmark Track

Architectural Trade-offs in Small Language Models Under Compute Constraints

小型语言模型在计算限制下的架构权衡

Shivraj Singh Bhatti

专题命中 效率与部署 ：language model(title,abstract)；small language model(title,abstract)；large language model(abstract)；分类 cs.CL、cs.LG

AI总结 研究探讨了小型语言模型在计算限制下的架构选择权衡，发现基于注意力的模型在效率上优于MLP，但过度增加深度或上下文会损害性能，且RoPE等技术在小型模型中效果有限。

Comments 15 pages, 11 images

V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval

V-Rex: 通过动态KV缓存检索实现实时视频大语言模型加速

Donghyuk Kim, Sejeong Yang, Wonjin Shin, Joo-Young Kim

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结 V-Rex通过动态KV缓存检索算法和硬件加速器，实现边缘设备上的实时视频LLM推理，显著提升速度和能效。

Comments 14 pages, 20 figures, conference, accepted by HPCA 2026

Encrypted Traffic Detection in Resource Constrained IoT Networks: A Diffusion Model and LLM Integrated Framework

资源受限物联网网络中加密流量检测：扩散模型与大语言模型集成框架

Hongjuan Li, Hui Kang, Chenbang Liu, Ruolin Wang, Jiahui Li, Geng Sun, Jiacheng Wang, Shuang Liang, Shiwen Mao

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

AI总结 DMLITE通过结合扩散模型和大语言模型，有效提升资源受限物联网网络中加密流量检测的准确率和效率。

Comments This paper is accepted by IEEE Transactions on Network Science and Engineering

BitRL-Light: 1-bit LLM Agents with Deep Reinforcement Learning for Energy-Efficient Smart Home Lighting Optimization

BitRL-Light: 1位LLM代理结合深度强化学习用于节能智能家庭照明优化

Ravi Gupta, Shabista Haider

专题命中 效率与部署 ：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结 BitRL-Light利用1位量化LLM与深度强化学习，在边缘设备上实现智能家庭照明优化，达到显著能耗降低和高用户满意度。

Comments Presented as poster in IPCCC 2025 at Austin

Phishing Detection in the Gen-AI Era: Quantized LLMs vs Classical Models

在生成式AI时代进行钓鱼攻击检测：量化LLM与经典模型

Jikesh Thapa, Gurrehmat Chahal, Serban Voinea Gabreanu, Yazan Otoum

机构 * School of Computer Science and Technology（计算机科学与技术学院） 纠错

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

AI总结 本文比较了传统ML、DL和量化LLM在钓鱼检测中的性能，发现优化的LLM在准确率和效率上具有潜力，适合高效部署。

Comments 8 Pages, IEEE Conference

Input-Adaptive Visual Preprocessing for Efficient Fast Vision-Language Model Inference

面向高效视觉语言模型推理的输入自适应视觉预处理

Putu Indah Githa Cahyani, Komang David Dananjaya Suartana, Novanto Yudistira

机构 * Faculty of Computer Science, University of Brawijaya（计算机科学学院，布拉维亚大学） 纠错

专题命中 效率与部署 ：language model(title,abstract)

AI总结 本研究提出一种自适应视觉预处理方法，通过动态调整输入分辨率和空间覆盖，显著提升视觉语言模型的推理效率。

CoDrone: Autonomous Drone Navigation Assisted by Edge and Cloud Foundation Models

CoDrone：由边缘和云基础模型辅助的自主无人机导航

Pengyu Chen, Tao Ouyang, Ke Luo, Weijie Hong, Xu Chen

专题命中 效率与部署 ：foundation model(title,abstract)

AI总结 CoDrone通过整合云-边-端协作计算框架和基础模型，提升无人机自主导航性能，实现更高效和精确的环境感知与动态适应。

Comments This paper is accepted by the IEEE Internet of Things Journal (IoT-J) for publication in the Special Issue on "Augmented Edge Sensing Intelligence for Low-Altitude IoT Systems"

MultiMind at SemEval-2025 Task 7: Crosslingual Fact-Checked Claim Retrieval via Multi-Source Alignment

多思维在SemEval-2025任务7中的应用：通过多源对齐实现跨语言事实核查声明检索

Mohammad Mahdi Abootorabi, Alireza Ghahramani Kure, Mohammadali Mohammadkhani, Sina Elahimanesh, Mohammad Ali Ali Panah

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 TriAligner通过多源对齐和对比学习，实现跨语言事实核查声明的高效检索，提升多语言环境下的信息准确性。

Comments 11 pages Published at the SemEval-2025 workshop

ALIVE: An Avatar-Lecture Interactive Video Engine with Content-Aware Retrieval for Real-Time Interaction

ALIVE: 一种具有内容感知检索的虚拟形象-讲座交互视频引擎，用于实时交互

Md Zabirul Islam, Md Motaleb Hossen Manik, Ge Wang

机构 * Department of Computer Science Rensselaer Polytechnic Institute（计算机科学系罗切斯特理工学院） ； Department of Biomedical Engineering Rensselaer Polytechnic Institute（生物医学工程系罗切斯特理工学院） 纠错

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)

AI总结 ALIVE通过本地部署和内容感知检索，实现基于虚拟形象的实时互动学习，提升讲座的教育价值。

SingingSDS: A Singing-Capable Spoken Dialogue System for Conversational Roleplay Applications

SingingSDS: 一种具备歌唱能力的语音对话系统用于对话角色扮演应用

Jionghao Han, Jiatong Shi, Masao Someki, Yuxun Tang, Lan Liu, Yiwen Zhao, Wenhao Feng, Shinji Watanabe

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Renmin University of China（中国人民大学） 纠错

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)

AI总结 SingingSDS是一种通过歌唱回应的语音对话系统，旨在通过更情感化和愉悦的交互提升角色扮演和互动娱乐体验。

Stochastic activations

随机激活

Maria Lomeli, Matthijs Douze, Gergely Szilvasy, Loic Cabannes, Jade Copet, Sainbayar Sukhbaatar, Jason Weston, Gabriel Synnaeve, Pierre-Emmanuel Mazaré, Hervé Jégou

机构 * Paris Cité University（巴黎公民大学） 纠错

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

AI总结 随机激活通过在预训练中使用随机非线性函数并微调时使用RELU，提高推理效率和生成文本多样性。

Data-Free Pruning of Self-Attention Layers in LLMs

无需数据的LLM自注意力层剪枝

Dhananjay Saikumar, Blesson Varghese

机构 * School of Computer Science（计算机科学学院） ； University of St Andrews（圣安德鲁大学） 纠错

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

AI总结 无需数据的LLM自注意力层剪枝方法通过Gate-Norm实现高效模型压缩，提升推理吞吐量并保持高准确率。

Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual Accuracy

压缩因果推理：量化与图RAG对干预和反事实准确率的影响

Steve Nwaiwu, Nipat Jongsawat, Anucha Tungkasthan

机构 * School of Data and Information（数据与信息学院） ； Rajamangala University of Technology（拉贾穆angala技术大学） 纠错

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结 研究探讨量化与图结构增强对因果推理准确率的影响，发现四比特量化对因果推理具有鲁棒性，图结构增强可提升干预准确性，现有反事实基准需改进以捕捉更深层次因果脆弱性。

When LLMs fall short in Deductive Coding: Model Comparison and Human AI Collaboration Workflow Design

当LLM在演绎编码中表现不足：模型比较与人机协作工作流设计

Zijian Li, Luzhen Tang, Mengyu Xia, Xinyu Li, Naping Chen, Dragan Gašević, Yizhou Fan

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)

AI总结 本研究探讨了LLM在演绎编码中的局限性，通过模型比较和人机协作工作流设计，揭示了人类判断的重要性及协作编码的实用价值。

Comments 24 pages (8 pages for Appendix), 4 figures, for Learning Analytics & Knowledge Conference to be held in 2026, Norway (LAK26)

Diving into 3D Parallelism with Heterogeneous Spot Instance GPUs: Design and Implications

深入研究异构斑点实例GPU中的3D并行性：设计与影响

Yuxiao Wang, Yuedong Xu, Qingyang Duan, Yuxuan Liu, Lei Jiao, Yinghao Yu, Jun Wu

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)

AI总结 AutoHet通过自动优化异构GPU的3D并行计划，实现分布式训练的高效性和恢复速度提升。

NVIDIA Nemotron 3: Efficient and Open Intelligence

NVIDIA Nemotron 3：高效且开放的智能

NVIDIA, :, Aaron Blakeman, Aaron Grattafiori, Aarti Basant, Abhibha Gupta, Abhinav Khattar, Adi Renduchintala, Aditya Vavre, Akanksha Shukla, Akhiad Bercovich, Aleksander Ficek, Aleksandr Shaposhnikov, Alex Kondratenko, Alexander Bukharin, Alexandre Milesi, Ali Taghibakhshi, Alisa Liu, Amelia Barton, Ameya Sunil Mahabaleshwarkar, Amir Klein, Amit Zuker, Amnon Geifman, Amy Shen, Anahita Bhiwandiwalla, Andrew Tao, Anjulie Agrusa, Ankur Verma, Ann Guan, Anubhav Mandarwal, Arham Mehta, Ashwath Aithal, Ashwin Poojary, Asif Ahamed, Asit Mishra, Asma Kuriparambil Thekkumpate, Ayush Dattagupta, Banghua Zhu, Bardiya Sadeghi, Barnaby Simkin, Ben Lanir, Benedikt Schifferer, Besmira Nushi, Bilal Kartal, Bita Darvish Rouhani, Boris Ginsburg, Brandon Norick, Brandon Soubasis, Branislav Kisacanin, Brian Yu, Bryan Catanzaro, Carlo del Mundo, Chantal Hwang, Charles Wang, Cheng-Ping Hsieh, Chenghao Zhang, Chenhan Yu, Chetan Mungekar, Chintan Patel, Chris Alexiuk, Christopher Parisien, Collin Neale, Cyril Meurillon, Damon Mosk-Aoyama, Dan Su, Dane Corneil, Daniel Afrimi, Daniel Lo, Daniel Rohrer, Daniel Serebrenik, Daria Gitman, Daria Levy, Darko Stosic, David Mosallanezhad, Deepak Narayanan, Dhruv Nathawani, Dima Rekesh, Dina Yared, Divyanshu Kakwani, Dong Ahn, Duncan Riach, Dusan Stosic, Edgar Minasyan, Edward Lin, Eileen Long, Eileen Peters Long, Elad Segal, Elena Lantz, Ellie Evans, Elliott Ning, Eric Chung, Eric Harper, Eric Tramel, Erick Galinkin, Erik Pounds, Evan Briones, Evelina Bakhturina, Evgeny Tsykunov, Faisal Ladhak, Fay Wang, Fei Jia, Felipe Soares, Feng Chen, Ferenc Galko, Frank Sun, Frankie Siino, Gal Hubara Agam, Ganesh Ajjanagadde, Gantavya Bhatt, Gargi Prasad, George Armstrong, Gerald Shen, Gorkem Batmaz, Grigor Nalbandyan, Haifeng Qian, Harsh Sharma, Hayley Ross, Helen Ngo, Herbert Hum, Herman Sahota, Hexin Wang, Himanshu Soni, Hiren Upadhyay, Huizi Mao, Huy C Nguyen, Huy Q Nguyen, Iain Cunningham, Ido Galil, Ido Shahaf, Igor Gitman, Ilya Loshchilov, Itamar Schen, Itay Levy, Ivan Moshkov, Izik Golan, Izzy Putterman, Jan Kautz, Jane Polak Scowcroft, Jared Casper, Jatin Mitra, Jeffrey Glick, Jenny Chen, Jesse Oliver, Jian Zhang, Jiaqi Zeng, Jie Lou, Jimmy Zhang, Jinhang Choi, Jining Huang, Joey Conway, Joey Guman, John Kamalu, Johnny Greco, Jonathan Cohen, Joseph Jennings, Joyjit Daw, Julien Veron Vialard, Junkeun Yi, Jupinder Parmar, Kai Xu, Kan Zhu, Kari Briski, Katherine Cheung, Katherine Luna, Keith Wyss, Keshav Santhanam, Kevin Shih, Kezhi Kong, Khushi Bhardwaj, Kirthi Shankar, Krishna C. Puvvada, Krzysztof Pawelec, Kumar Anik, Lawrence McAfee, Laya Sleiman, Leon Derczynski, Li Ding, Lizzie Wei, Lucas Liebenwein, Luis Vega, Maanu Grover, Maarten Van Segbroeck, Maer Rodrigues de Melo, Mahdi Nazemi, Makesh Narsimhan Sreedhar, Manoj Kilaru, Maor Ashkenazi, Marc Romeijn, Marcin Chochowski, Mark Cai, Markus Kliegl, Maryam Moosaei, Matt Kulka, Matvei Novikov, Mehrzad Samadi, Melissa Corpuz, Mengru Wang, Meredith Price, Michael Andersch, Michael Boone, Michael Evans, Miguel Martinez, Mikail Khona, Mike Chrzanowski, Minseok Lee, Mohammad Dabbah, Mohammad Shoeybi, Mostofa Patwary, Nabin Mulepati, Najeeb Nabwani, Natalie Hereth, Nave Assaf, Negar Habibi, Neta Zmora, Netanel Haber, Nicola Sessions, Nidhi Bhatia, Nikhil Jukar, Nikki Pope, Nikolai Ludwig, Nima Tajbakhsh, Nir Ailon, Nirmal Juluru, Nishant Sharma, Oleksii Hrinchuk, Oleksii Kuchaiev, Olivier Delalleau, Oluwatobi Olabiyi, Omer Ullman Argov, Omri Puny, Oren Tropp, Ouye Xie, Parth Chadha, Pasha Shamis, Paul Gibbons, Pavlo Molchanov, Pawel Morkisz, Peter Dykas, Peter Jin, Pinky Xu, Piotr Januszewski, Pranav Prashant Thombre, Prasoon Varshney, Pritam Gundecha, Przemek Tredak, Qing Miao, Qiyu Wan, Rabeeh Karimi Mahabadi, Rachit Garg, Ran El-Yaniv, Ran Zilberstein, Rasoul Shafipour, Rich Harang, Rick Izzo, Rima Shahbazyan, Rishabh Garg, Ritika Borkar, Ritu Gala, Riyad Islam, Robert Hesse, Roger Waleffe, Rohit Watve, Roi Koren, Ruoxi Zhang, Russell Hewett, Russell J. Hewett, Ryan Prenger, Ryan Timbrook, Sadegh Mahdavi, Sahil Modi, Samuel Kriman, Sangkug Lim, Sanjay Kariyappa, Sanjeev Satheesh, Saori Kaji, Satish Pasumarthi, Saurav Muralidharan, Sean Narentharen, Sean Narenthiran, Seonmyeong Bak, Sergey Kashirsky, Seth Poulos, Shahar Mor, Shanmugam Ramasamy, Shantanu Acharya, Shaona Ghosh, Sharath Turuvekere Sreenivas, Shelby Thomas, Shiqing Fan, Shreya Gopal, Shrimai Prabhumoye, Shubham Pachori, Shubham Toshniwal, Shuoyang Ding, Siddharth Singh, Simeng Sun, Smita Ithape, Somshubra Majumdar, Soumye Singhal, Stas Sergienko, Stefania Alborghetti, Stephen Ge, Sugam Dipak Devare, Sumeet Kumar Barua, Suseella Panguluri, Suyog Gupta, Sweta Priyadarshi, Syeda Nahida Akter, Tan Bui, Teodor-Dumitru Ene, Terry Kong, Thanh Do, Tijmen Blankevoort, Tim Moon, Tom Balough, Tomer Asida, Tomer Bar Natan, Tomer Ronen, Tugrul Konuk, Twinkle Vashishth, Udi Karpas, Ushnish De, Vahid Noorozi, Vahid Noroozi, Venkat Srinivasan, Venmugil Elango, Victor Cui, Vijay Korthikanti, Vinay Rao, Vitaly Kurin, Vitaly Lavrukhin, Vladimir Anisimov, Wanli Jiang, Wasi Uddin Ahmad, Wei Du, Wei Ping, Wenfei Zhou, Will Jennings, William Zhang, Wojciech Prazuch, Xiaowei Ren, Yashaswi Karnati, Yejin Choi, Yev Meyer, Yi-Fu Wu, Yian Zhang, Yigong Qin, Ying Lin, Yonatan Geifman, Yonggan Fu, Yoshi Subara, Yoshi Suhara, Yubo Gao, Zach Moshe, Zhen Dong, Zhongbo Zhu, Zihan Liu, Zijia Chen, Zijie Yan

机构 * NVIDIA 纠错

专题命中 效率与部署 ：post-training(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 NVIDIA推出的Nemotron 3系列模型通过混合Mamba-Transformer架构实现高效推理与大上下文长度，提供多种规模模型以满足不同应用场景需求。

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Nemotron 3 Nano：开放、高效专家混合混合Mamba-Transformer模型用于代理推理

NVIDIA, :, Aaron Blakeman, Aaron Grattafiori, Aarti Basant, Abhibha Gupta, Abhinav Khattar, Adi Renduchintala, Aditya Vavre, Akanksha Shukla, Akhiad Bercovich, Aleksander Ficek, Aleksandr Shaposhnikov, Alex Kondratenko, Alexander Bukharin, Alexandre Milesi, Ali Taghibakhshi, Alisa Liu, Amelia Barton, Ameya Sunil Mahabaleshwarkar, Amir Klein, Amit Zuker, Amnon Geifman, Amy Shen, Anahita Bhiwandiwalla, Andrew Tao, Ann Guan, Anubhav Mandarwal, Arham Mehta, Ashwath Aithal, Ashwin Poojary, Asif Ahamed, Asma Kuriparambil Thekkumpate, Ayush Dattagupta, Banghua Zhu, Bardiya Sadeghi, Barnaby Simkin, Ben Lanir, Benedikt Schifferer, Besmira Nushi, Bilal Kartal, Bita Darvish Rouhani, Boris Ginsburg, Brandon Norick, Brandon Soubasis, Branislav Kisacanin, Brian Yu, Bryan Catanzaro, Carlo del Mundo, Chantal Hwang, Charles Wang, Cheng-Ping Hsieh, Chenghao Zhang, Chenhan Yu, Chetan Mungekar, Chintan Patel, Chris Alexiuk, Christopher Parisien, Collin Neale, Damon Mosk-Aoyama, Dan Su, Dane Corneil, Daniel Afrimi, Daniel Rohrer, Daniel Serebrenik, Daria Gitman, Daria Levy, Darko Stosic, David Mosallanezhad, Deepak Narayanan, Dhruv Nathawani, Dima Rekesh, Dina Yared, Divyanshu Kakwani, Dong Ahn, Duncan Riach, Dusan Stosic, Edgar Minasyan, Edward Lin, Eileen Long, Eileen Peters Long, Elena Lantz, Ellie Evans, Elliott Ning, Eric Chung, Eric Harper, Eric Tramel, Erick Galinkin, Erik Pounds, Evan Briones, Evelina Bakhturina, Faisal Ladhak, Fay Wang, Fei Jia, Felipe Soares, Feng Chen, Ferenc Galko, Frankie Siino, Gal Hubara Agam, Ganesh Ajjanagadde, Gantavya Bhatt, Gargi Prasad, George Armstrong, Gerald Shen, Gorkem Batmaz, Grigor Nalbandyan, Haifeng Qian, Harsh Sharma, Hayley Ross, Helen Ngo, Herman Sahota, Hexin Wang, Himanshu Soni, Hiren Upadhyay, Huizi Mao, Huy C Nguyen, Huy Q Nguyen, Iain Cunningham, Ido Shahaf, Igor Gitman, Ilya Loshchilov, Ivan Moshkov, Izzy Putterman, Jan Kautz, Jane Polak Scowcroft, Jared Casper, Jatin Mitra, Jeffrey Glick, Jenny Chen, Jesse Oliver, Jian Zhang, Jiaqi Zeng, Jie Lou, Jimmy Zhang, Jining Huang, Joey Conway, Joey Guman, John Kamalu, Johnny Greco, Jonathan Cohen, Joseph Jennings, Joyjit Daw, Julien Veron Vialard, Junkeun Yi, Jupinder Parmar, Kai Xu, Kan Zhu, Kari Briski, Katherine Cheung, Katherine Luna, Keshav Santhanam, Kevin Shih, Kezhi Kong, Khushi Bhardwaj, Krishna C. Puvvada, Krzysztof Pawelec, Kumar Anik, Lawrence McAfee, Laya Sleiman, Leon Derczynski, Li Ding, Lucas Liebenwein, Luis Vega, Maanu Grover, Maarten Van Segbroeck, Maer Rodrigues de Melo, Makesh Narsimhan Sreedhar, Manoj Kilaru, Maor Ashkenazi, Marc Romeijn, Mark Cai, Markus Kliegl, Maryam Moosaei, Matvei Novikov, Mehrzad Samadi, Melissa Corpuz, Mengru Wang, Meredith Price, Michael Boone, Michael Evans, Miguel Martinez, Mike Chrzanowski, Mohammad Shoeybi, Mostofa Patwary, Nabin Mulepati, Natalie Hereth, Nave Assaf, Negar Habibi, Neta Zmora, Netanel Haber, Nicola Sessions, Nidhi Bhatia, Nikhil Jukar, Nikki Pope, Nikolai Ludwig, Nima Tajbakhsh, Nirmal Juluru, Oleksii Hrinchuk, Oleksii Kuchaiev, Olivier Delalleau, Oluwatobi Olabiyi, Omer Ullman Argov, Ouye Xie, Parth Chadha, Pasha Shamis, Pavlo Molchanov, Pawel Morkisz, Peter Dykas, Peter Jin, Pinky Xu, Piotr Januszewski, Pranav Prashant Thombre, Prasoon Varshney, Pritam Gundecha, Qing Miao, Rabeeh Karimi Mahabadi, Ran El-Yaniv, Ran Zilberstein, Rasoul Shafipour, Rich Harang, Rick Izzo, Rima Shahbazyan, Rishabh Garg, Ritika Borkar, Ritu Gala, Riyad Islam, Roger Waleffe, Rohit Watve, Roi Koren, Ruoxi Zhang, Russell J. Hewett, Ryan Prenger, Ryan Timbrook, Sadegh Mahdavi, Sahil Modi, Samuel Kriman, Sanjay Kariyappa, Sanjeev Satheesh, Saori Kaji, Satish Pasumarthi, Sean Narentharen, Sean Narenthiran, Seonmyeong Bak, Sergey Kashirsky, Seth Poulos, Shahar Mor, Shanmugam Ramasamy, Shantanu Acharya, Shaona Ghosh, Sharath Turuvekere Sreenivas, Shelby Thomas, Shiqing Fan, Shreya Gopal, Shrimai Prabhumoye, Shubham Pachori, Shubham Toshniwal, Shuoyang Ding, Siddharth Singh, Simeng Sun, Smita Ithape, Somshubra Majumdar, Soumye Singhal, Stefania Alborghetti, Stephen Ge, Sugam Dipak Devare, Sumeet Kumar Barua, Suseella Panguluri, Suyog Gupta, Sweta Priyadarshi, Syeda Nahida Akter, Tan Bui, Teodor-Dumitru Ene, Terry Kong, Thanh Do, Tijmen Blankevoort, Tom Balough, Tomer Asida, Tomer Bar Natan, Tugrul Konuk, Twinkle Vashishth, Udi Karpas, Ushnish De, Vahid Noorozi, Vahid Noroozi, Venkat Srinivasan, Venmugil Elango, Vijay Korthikanti, Vitaly Kurin, Vitaly Lavrukhin, Wanli Jiang, Wasi Uddin Ahmad, Wei Du, Wei Ping, Wenfei Zhou, Will Jennings, William Zhang, Wojciech Prazuch, Xiaowei Ren, Yashaswi Karnati, Yejin Choi, Yev Meyer, Yi-Fu Wu, Yian Zhang, Ying Lin, Yonatan Geifman, Yonggan Fu, Yoshi Subara, Yoshi Suhara, Yubo Gao, Zach Moshe, Zhen Dong, Zihan Liu, Zijia Chen, Zijie Yan

机构 * NVIDIA 纠错

专题命中 效率与部署 ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 Nemotron 3 Nano是一种高效混合Mamba-Transformer模型，通过预训练和微调在代理推理任务中实现更高准确性和吞吐量。

Designing Spatial Architectures for Sparse Attention: STAR Accelerator via Cross-Stage Tiling

为稀疏注意力设计空间架构：通过跨阶段分片的STAR加速器

Huizheng Wang, Taiquan Wei, Hongbin Wang, Zichuan Wang, Xinru Tang, Zhiheng Yue, Shaojun Wei, Yang Hu, Shouyi Yin

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)

AI总结 STAR加速器通过跨阶段分片技术提升Transformer推理效率，实现9.2倍速度和71.2倍能效，同时优化多核架构以处理超长序列。

Comments Accepted for publication in IEEE Transactions on Computers. In this version, we have corrected the missing author information in the references

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

自回归模型中涌现的时间抽象使分层强化学习成为可能

Seijin Kobayashi, Yanick Schimpf, Maximilian Schlegel, Angelika Steger, Maciej Wolczyk, Johannes von Oswald, Nino Scherrer, Kaitlin Maile, Guillaume Lajoie, Blake A. Richards, Rif A. Saurous, James Manyika, Blaise Agüera y Arcas, Alexander Meulemans, João Sacramento

机构 * Google, Paradigms of Intelligence Team（谷歌，智能范式团队） 纠错

专题命中 效率与部署 ：foundation model(abstract)；分类 cs.AI、cs.LG

AI总结 自回归模型通过内部强化学习实现时间抽象，提升稀疏奖励下的分层强化学习效率。

AI-Driven Decision-Making System for Hiring Process

基于人工智能的招聘过程决策系统

Vira Filatova, Andrii Zelenchuk, Dmytro Filatov

机构 * Applied Artificial Intelligence Covijn Ltd.（应用人工智能公司Covijn Ltd.） ； Computer Vision Aimech Technologies Corp.（计算机视觉公司Aimech Technologies Corp.） 纠错

专题命中 效率与部署 ：LLM(abstract)；分类 cs.AI

AI总结 本文提出了一种基于人工智能的模块化多智能体招聘助手，通过整合文档处理、结构化档案构建、公开数据验证和风险惩罚评分，提高招聘效率并降低筛选成本，同时保留人类决策作为最终权威。

Comments 10 pages, 3 figures

Fast SAM2 with Text-Driven Token Pruning

快速SAM2与文本驱动的标记剪枝

Avilasha Mandal, Chaoning Zhang, Fachrina Dewi Puspitasari, Xudong Wang, Jiaquan Zhang, Caiyan Qin, Guoqing Wang, Yang Yang, Heng Tao Shen

机构 * School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院） ； Department of Computer Science and Engineering, Indian Institute of Technology, Delhi（印度理工学院德里分校计算机科学与工程系） ； School of Robotics and Advanced Manufacture, Harbin Institute of Technology（哈尔滨工业大学机器人与先进制造学院） 纠错

专题命中 效率与部署 ：foundation model(abstract)

AI总结 本文提出文本驱动的标记剪枝方法，提升SAM2视频分割效率，实现推理速度提升42.50%和内存使用降低37.41%。

Comments 28 pages, 9 figures

Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection

引导视觉-语言预训练模型进行增量面部呈现攻击检测

Haoze Li, Jie Zhang, Guoying Zhao, Stephen Lin, Shiguang Shan

机构 * School of Computer Science, China University of Geosciences（中国地质大学（北京）计算机科学学院） ； State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences (CAS)（中国科学院人工智能安全重点实验室） ； University of China Academy of Sciences（中国科学院大学） ； Center for Machine Vision and Signal Analysis, University of Oulu（奥卢大学机器视觉与信号分析中心） ； Microsoft Research Asia（微软亚洲研究院） 纠错

专题命中 效率与部署 ：prompting(abstract)

AI总结 SVLP-IL是一种基于视觉-语言预训练模型的增量学习框架，通过多方面提示和选择性弹性权重固化方法，在隐私合规的前提下提升面部呈现攻击检测的鲁棒性。

RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation

RGMP: 基于几何先验的多模态策略用于通用人形机器人操作

Xuetao Li, Wenke Huang, Nengyuan Pan, Kaiyan Zhao, Songhua Yang, Yiming Wang, Mengde Li, Mang Ye, Jifeng Xuan, Miao Li

专题命中 效率与部署 ：language model(abstract)

AI总结 RGMP通过结合几何-语义推理与递归高斯适应，实现了高效的人形机器人多模态操作控制。

Journal ref Proceedings of the AAAI conference on artificial intelligence, 2026

MMSRARec: Summarization and Retrieval Augumented Sequential Recommendation Based on Multimodal Large Language Model

MMSRARec: 基于多模态大语言模型的摘要与检索增强的序列推荐

Haoyu Wang, Yitong Wang, Jining Wang

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)

AI总结 本文提出MMSRARec，基于多模态大语言模型，通过摘要与检索增强序列推荐，提升推荐性能、可解释性与计算效率。

Comments Under Review

Emotion Diffusion in Real and Simulated Social Graphs: Structural Limits of LLM-Based Social Simulation

现实与模拟社交图中的情感扩散：基于大语言模型的社会模拟的结构限制

Qiqi Qiang

专题命中 领域大模型 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

AI总结 本研究比较了现实与模拟社交图中的情感扩散，发现LLM生成的数据在结构和动态上存在显著差异，影响下游任务性能。