论文列表 - OurXiv

新用户从这里开始

先选订阅词（如 RAG、multimodal、Agent），每周自动看到相关新论文。
在列表页点开感兴趣论文，点击“赞助解读”得到结构化结论与可执行动作。
把高价值解读分享到团队/社群，协同节省阅读成本。

设置我的订阅看行业动作洞察

每周精选

近7天内社区解读较多的方向与热门关键词，适合先读一眼再决定是否深入。

arabic task resource audio speech tasks ads cs sd llms

Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic AudioLLMs

Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury

cs.SD 解读时间：07-02

你还没有订阅任何关键词，以下为站点默认关键词展示的最新论文，全站新人看到的内容相同，并非针对你的个性化推荐。想看专属内容？去订阅自己感兴趣的关键词。

标题	arXiv	发布时间	状态
GEPA-Curator: Curated Learning for Self Improving Agents Zack Yu, Nicholas Lee, Minjae Lee, Lakshya Agarwal, Luca Manolache, Wonjun Kang, Matei Zaharia, Michael W. Mahoney, Kurt Keutzer, Sehoon Kim, Amir Gholami cs.CL cs.CL	2610.37651v1	2026-10-27 17:58:11	待赞助
Can LLMs Uncover Hidden Physical Laws through Free Exploration? Zhen Yang, Wen Wang, Xander Xu, Ying-Cong Chen cs.CL cs.CL cs.AI cs.MA	2610.37649v1	2026-10-27 17:57:00	待赞助
Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis Andrew Szot, Samira Abnar, Omar Attia, Abbas Kazerouni, Michael Kirchhof, Cheng-Yu Hsieh, Raviteja Vemulapalli, Alexander Toshev cs.LG cs.LG	2610.37648v1	2026-10-27 17:56:46	待赞助
MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control Athanasios Glentis, Dawei Li, Mingyi Hong cs.LG cs.LG cs.AI math.OC	2610.37647v1	2026-10-27 17:56:40	待赞助
Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions Anouar Imel, Imad Charradi, Abderrahman Sghir, Khalil El Khammar cs.AI cs.AI cs.CL cs.MA	2610.37624v1	2026-10-27 17:49:39	待赞助
VideoLVR: Latent Visual Reasoning over Grounded Video Evidence Shilong Li, Xingyuan Bu, Hao Shi, Yun Xing, Weixin Feng, Qiangpeng Yang, Shilei Wen cs.CV cs.CV cs.AI	2610.37613v1	2026-10-27 17:41:56	待赞助
LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation Nesta Midavaine, Floris Fok, Paulo Mendes, Joao Silva, Önder Akaçık, Dimas Lima, Zülküf Genç cs.LG cs.LG cs.IR	2610.37570v1	2026-10-27 17:15:15	待赞助
Boundary Plateau Laws II Camillo De Lellis, Federico Glaudo math.AP math.AP math-ph math.DG	2610.37560v1	2026-10-27 17:08:05	待赞助
Orthogonal and Parametrized Multi-Attribute Steering of LLMs Remy Ogasawara, Cullen Anderson, Narmeen Fatimah Oozeer, Foad Namjoo, Amir Abdullah, Jens Kristian Refsgaard Schou, Jeff M. Phillips cs.LG cs.LG cs.AI	2610.37517v1	2026-10-27 16:39:53	待赞助
Teach reality, not ethics: a drop-in continued-pretraining corpus installs coupled human-biosphere-AI welfare dispositions across model families Trent R. Northen, Mingxun Wang cs.CL cs.CL	2610.37484v1	2026-10-27 16:11:04	待赞助
Follow the Gradient: Tracing Safety Degradation Back to Training Data Saket Reddy, Amro Abbas, Anshuman Suri, Ari Morcos, David Schwab, Pratyush Maini cs.LG cs.LG cs.AI cs.CL	2610.37481v1	2026-10-27 16:08:08	待赞助
Concordat: Typed Sessions for LLM Agents Milad Sikaroudi cs.AI cs.AI cs.MA	2610.37461v1	2026-10-27 16:00:26	待赞助
Interpretable Meta-Policies for Neural Decision Making Raban Emunds, Jannis Blüml, Quentin Delfosse, Kristian Kersting cs.LG cs.LG	2610.37451v1	2026-10-27 15:55:05	待赞助
ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents Xinying Qian, Ying Zhang, Yu Zhao, Xubo Liu, Baohang Zhou, Jeff Z. Pan cs.CL cs.CL	2610.37443v1	2026-10-27 15:51:42	待赞助
Request-Adaptive Execution for Efficient Hybrid LLM Inference Fahao Chen, Xuzhe Yan, Qi Zhang, Peng Li, Dongxiao Yu, Song Guo cs.DC cs.DC	2610.37432v1	2026-10-27 15:43:30	待赞助
Bayes-Adaptive MDPs for Rollout Allocation to Enhance GRPO Training Faeze Moradi Kalarde, Armin Toroghi, Nam Ho Koh, Doo Hwan Hwang, Seungjin Kim, Kee-Eung Kim, Scott Sanner cs.LG cs.LG cs.AI	2610.37429v1	2026-10-27 15:41:57	待赞助
The Envelope Layer: An Underestimated Surface of LLM Agent Defense Yuelin Han cs.CR cs.CR	2610.37415v1	2026-10-27 15:32:10	待赞助
Clearing the FoG: Training KG Agents to Retrieve the Evidence Behind Their Answers Zongyuan Sun, Shuai Zhao, Yingjun Du, Ke Shu, Ziyue Zhu, Haoran Luo cs.AI cs.AI	2610.37405v1	2026-10-27 15:20:37	待赞助
Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data Geunhyoung Kim, Sung Ju Hwang cs.LG cs.LG cs.AI	2610.37386v1	2026-10-27 15:11:35	待赞助
Same Verdict, Different Readers: Personalizing Fact-Checking Explanations from Relative Preferences Haokun Wen, Xuemeng Song, Mong-Li Lee, Wynne Hsu cs.CL cs.CL	2610.37380v1	2026-10-27 15:08:30	待赞助