| 1 | Propose-Filter-Release: Scaling Noise to Typical Sensitivity via Private Filtering | Moshe Shenfeld, Eliad Tsfadia, Katrina Ligett | cs.LG | 2026-10-29 |
| 2 | Fight World Model: Customizable Combat through Visual Interaction Proxies | Jiahua Li, Zixu John, Tom Zhong +5 | cs.CV | 2026-10-29 |
| 3 | VeriCUA: Verification as Agentic Exploration for Computer-Using Agents | Qiushi Sun, Da Yu, Alexander Knop +5 | cs.AI | 2026-10-29 |
| #4 | Gym-Anything for Robotics: Scaling physical simulations with digital agents | Pranjal Aggarwal, Sean Welleck | cs.RO | 2026-10-29 |
| #5 | How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates | Max Neuwinger, Hanna Yukhymenko, Imanol Schlag | cs.CL | 2026-10-29 |
| #6 | Numerical Integration on Bounded Domains via Learned Reflected Diffusions | Kirill Korolev, Artur Goldman, Timofei Gritsaev +2 | cs.LG | 2026-10-29 |
| #7 | Glance: The Generator Is Its Own Reranker | Adilet Metinov, Chingiz Arziev | cs.CL | 2026-10-29 |
| #8 | Framework-Conditional Open Materials Generation | Maya M. Martirossyan, Hillary Pan, Philipp Höllmer +1 | cs.LG | 2026-10-29 |
| #9 | A Pretrained Model for Bayesian Filtering in Heterogeneous Dynamical Systems | Ke Fan, Wen Wu, Haitao Su +3 | cs.LG | 2026-10-29 |
| #10 | Continuous-Action World Models: Learning Cross-Embodiment Spatiotemporal Dynamics Priors | Liangyu Li, Qingwen Liu | cs.RO | 2026-10-29 |
| #11 | Scaling Mathematical Proof Supervision from Structured Textbooks | Youqing Fang, Zhouqi Hua, Yinhao Tang +7 | cs.CL | 2026-10-29 |
| #12 | How to Loop Your Transformer: Loop Scaling, Specialization, and Parallel Inference | Chanakya Ekbote, Artidoro Pagnoni, Devendra Singh Sachan +5 | cs.LG | 2026-10-29 |
| #13 | When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications | Yishuo Cai, Minzheng Wang, Liang Zhao +5 | cs.SE | 2026-10-29 |
| #14 | Conformal Annotation with Randomized Expert Review: Application to Online Cell-Type Labeling | Xuhe Zhang, Zhi Huang, Ying Jin | stat.ME | 2026-10-29 |
| #15 | Understanding axial attention in TSFMs through single location regression | Andrei-Tiberiu Pantea, Aymeric Dieuleveut | stat.ML | 2026-10-29 |
| #16 | Closing the Log Gap: Minimax-Optimal Regret for Episodic RL | Guy Zamir, Victor Boone, Matthew Zurek +1 | cs.LG | 2026-10-29 |
| #17 | ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformer | Wenxi Li, Jingchen Huang, Chenyang Lyu +4 | cs.CV | 2026-10-29 |
| #18 | Attention, Dynamic Wave and Hybrid Sequence Mixers in Language Models | Dmytro Babarytskyi, Oleksandr Babarytskyi | cs.LG | 2026-10-29 |
| #19 | Activation Probes Are Reliable With a Handful of Positive Examples | Riya Tyagi, Stefan Heimersheim | cs.LG | 2026-10-29 |
| #20 | Where Do Vision Language Models Fail at 3D Reasoning? | Khai Le-Duc, Nguyen Kim Hai Bui, An Ngo +11 | cs.CV | 2026-10-29 |
| #21 | The Real Cost of Context: Predicting Compute Time and Energy Consumption in LLM Prefill and Decode Phases | Lars Krupp, Daniel Geißler, Francisco M. Calatrava-Nicolas +3 | cs.AI | 2026-10-29 |
| #22 | Operator-Aware Posterior Sampling for Multivariate Weather Downscaling | Carlo Saccardi, Rudolf Saathof, Geethu Joseph +1 | cs.CV | 2026-10-29 |
| #23 | Comprehensive empirical evaluation of feature extractors in computer vision | Murat Isik | cs.CV | 2026-10-29 |
| #24 | Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute? | Qi Wang, Yun Qu, Lizhou Cai +10 | cs.AI | 2026-10-29 |
| #25 | LinQuant: Functional Invariances for Low-Precision Linear Recurrences | Neehal Tumma, Philipp Nazari, Rohan Cherukuri +2 | cs.LG | 2026-10-29 |
| #26 | Proving and Improving the Platonic Representation Hypothesis with JEPAs | Randall Balestriero, Yann LeCun | cs.AI | 2026-10-29 |
| #27 | PRISM: Personalized Item Representations in User History | Renzhi Wu, Zikun Cui, Junjie Yang +6 | cs.IR | 2026-10-29 |
| #28 | DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3 | Hong Lin, Zhongle Xie, Lidan Shou +2 | cs.CR | 2026-10-29 |
| #29 | Certified Access: Test-Time Compute on Conservative Physics-Structured AI Memory | Pratik Jawahar, Riccardo Maggioni, Jonas Petersen +5 | cs.AI | 2026-10-29 |
| #30 | Data Scaling Laws in Stereo Matching: From In-domain Fitting to Cross-domain Generalization | Tong Zhao, Di Liang, Yiming Zeng +3 | cs.CV | 2026-10-28 |
| #31 | From the Superderivative to a Relative-Gradient Edge Operator | Alejandro Garnung Menéndez | eess.IV | 2026-10-28 |
| #32 | Does Chain-of-Thought Reliance Follow a Scaling Law?Larger Models Follow Their Steps More, Independent of Post-Training | Esther Xin | cs.CL | 2026-10-28 |
| #33 | SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning | Qirui Liu, Wei Cao, Yu Mi +5 | cs.AI | 2026-10-28 |
| #34 | Compute Has Shape: Self-Morphing the Internal Computation of Frozen LLMs | Junxi Wu, Yiwen Guo, Shu-Tao Xia | cs.AI | 2026-10-28 |
| #35 | Towards Reliable, Scalable, and Value-Aligned Generative Recommendation for Large-Scale Advertising | Yatong Xiao, Yibo Sheng, Lixiang Wang +7 | cs.IR | 2026-10-28 |
| #36 | LLM-PowerTrace: A Dataset of Time-Resolved GPU Power Traces for AI Compute | Jiansheng Wang, Jaskeerat Singh, Haochen Xu +6 | eess.SY | 2026-10-28 |
| #37 | BudSplat: Feed-forward 3D Gaussian Splatting under a Rendering Budget | Muyu Xu, Fangneng Zhan, Yu Wei +2 | cs.CV | 2026-10-28 |
| #38 | Rubricon: Automated Rubric Generation and Refinement for LLM Evaluation and Training | Ulyana Tkachenko, Hui Wen Goh, Guram Gogia +1 | cs.AI | 2026-10-28 |
| #39 | GearUp: DAG-aware Acceleration for Serverless Inference Serving via Slack-guided Pre-loading | Qi Qi, Yifan Sui, Hanfei Yu +2 | cs.DC | 2026-10-28 |
| #40 | Scaling Lean Theorem Proving for Real-World Code Verification | Debargha Ganguly, Divya Raghunathan, Dejan Jovanović +6 | cs.CL | 2026-10-28 |
| #41 | Replaying the Same Gradients at a Different $\varepsilon$: A Registered Test of the Fixed-Trajectory Account of Adam's $\varepsilon$ for One Rare Row | Lngel Kyo | cs.LG | 2026-10-28 |
| #42 | Same Label, Different Interface: Beyond Action-Space Labels in Robot Learning | Arshia Sangwan, Zhongyang Zhang | cs.RO | 2026-10-28 |
| #43 | Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI | NVIDIA, :, Aastha Jhunjhunwala +556 | cs.CL | 2026-10-28 |
| #44 | Finite-step statistical mechanics of scale-invariant learning: spectral equations of state and curvature transport | Alexander Itin | cond-mat.stat-mech | 2026-10-27 |
| #45 | New Multiple Descent Phenomena Induced by Heterogeneous Data | Mark-Anthony Moisescu-Pareja, Elvis Dohmatob | stat.ML | 2026-10-27 |
| #46 | VerifiedLab: Harnessing Knowns for Unknowns | Yu Yao, Jiayi Dong, Yang Yang +2 | cs.AI | 2026-10-27 |
| #47 | Echo: Scaling Visual Reinforcement Learning with Off-policy Experience | Gagan Khandate | cs.RO | 2026-10-27 |
| #48 | Improving Data-Constrained Scaling with Hyperparameter Transfer and Ensembling | Ethan Baron, Shmuel Berman, Anirudh Satheesh +3 | cs.LG | 2026-10-27 |
| #49 | Depth through Recurrence: Towards Ultra-Efficient On-Device ASR | Chen Feng, Tianyi Xu, Ramchalam Kinattinkara Ramakrishnan +5 | cs.LG | 2026-10-27 |
| #50 | Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis | Andrew Szot, Samira Abnar, Omar Attia +5 | cs.LG | 2026-10-27 |