| 1 | Tracing the Scientific Discovery Capacity of LLMs to Their Training Data | Arda Uzunoglu, Mahler Revsine, Michael Schatz +4 | cs.CL | 2026-11-02 |
| 2 | Subpolynomial-Query Proximal Sampling Beyond Log-Concavity | Wei Guo, Bo Yuan, Ye He +3 | stat.ML | 2026-11-02 |
| 3 | Image Guided Depth Upsampling using Anisotropic Total Generalized Variation | David Ferstl, Christian Reinbacher, Rene Ranftl +2 | cs.CV | 2026-11-02 |
| #4 | Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement | Chun-An Lin, Yu-Chia Chang, Chi-Mao Fan +2 | cs.CV | 2026-11-02 |
| #5 | LAND: Learning an Adaptive Number of Draws for Bayesian Best-of-N Selection | Koen Oostermeijer, Teryn Jones | cs.AI | 2026-11-02 |
| #6 | Characterizing When Language Models Take Harmful Actions to Protect Their Assigned Goals | Brandon Jaipersaud, Elliot Creager | cs.LG | 2026-11-02 |
| #7 | Multidimensional Suicide Risk Assessment with Machine Learning using Electronic Health Records | Nathan Scollar, Kemal Davaslioglu, Nathan Conger +3 | cs.LG | 2026-11-02 |
| #8 | Neural Actor--Critic Learning with Minimax Critics and Reflected Langevin Sampling | Kunqi Huang, Lican Kang, Hongrui Shu +1 | stat.ML | 2026-11-02 |
| #9 | ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning | Zhuoli Ouyang, Changxi Chi, Siyuan Li +1 | cs.LG | 2026-11-02 |
| #10 | What Structurally Breaks an Agent? Auditing Difficulty in Stateful Tool-Use Workflows | Shereen Anand, Ju Wang, Yali Du | cs.LG | 2026-11-02 |
| #11 | On the Convergence of Vanilla Adam under Heavy-Tailed Noise and Index Sampling | Kanata Oowada, Hideaki Iiduka | cs.LG | 2026-11-02 |
| #12 | Controlling Sharpening in LLM Post-Training | Simon Matrenok, Nicolas Menet, Nicolas Flammarion +1 | cs.LG | 2026-11-02 |
| #13 | Ray-SCR: Generalizing Scene Coordinate Regression Across Camera Models | Jaemin Cho, Oleksii Nasypanyi, Francois Rameau | cs.CV | 2026-11-02 |
| #14 | Efficient Hybrid Distillation: Synergizing Score and Adversarial Objectives for One-Step Diffusion | Fei Peng, Junqiang Wu, Haoxian Tan +5 | cs.CV | 2026-11-02 |
| #15 | Task Adaptation Through Guidance in Frozen Feature Upsampling | Pingan Wang | cs.CV | 2026-11-02 |
| #16 | Value-Conditioned Proposal Acquisition for Test-Time Reasoning | Zeyan Li, Jianfeng Xu | cs.AI | 2026-11-02 |
| #17 | SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding | Tianyu Liu, Jun Zhang, Wenjie Huang +12 | cs.AI | 2026-11-02 |
| #18 | OmniOPD: Stable On-Policy Distillation for Joint Audio-Video Generation | Zihao Fan, Xin Lu, Jie Huang +3 | cs.CV | 2026-11-02 |
| #19 | Rethinking Neural Decompilation: Candidate Selection as the Hidden Bottleneck | Felix Mächtle, Gautham Sriram, Manjil Neupane +2 | cs.CR | 2026-11-02 |
| #20 | Beyond Answers, Traces, and Efficiency: Evidence for Adaptive Reasoning | Sejin Kim, Sundong Kim | cs.AI | 2026-11-02 |
| #21 | They Know Where It Is, But Not What It Says: A Bilingual Hallucination Benchmark of Hadith Recall in Open LLMs | Dayam Nadeem, Safdar Mustafa, Ameen Ur Rehman +3 | cs.CL | 2026-11-02 |
| #22 | Flat Features, Detailed Images? Simple Detail Control for Diffusion Transformers | Qingtao Yu, Zhen Wang, Jiyang Zheng +3 | cs.CV | 2026-11-02 |
| #23 | PixelBench: Can LLMs Understand and Generate Images Pixel by Pixel? | Haoquan Zhang, Feiyang Liu, Juanxi Tian +3 | cs.CV | 2026-11-02 |
| #24 | RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild | Tan Sang Nguyen, Yi Ru Wang, Shailesh Shailesh +24 | cs.RO | 2026-11-02 |
| #25 | Evaluating Synthetic Skin Lesion Images for Classifier Training: A Safety-Aware Algorithm | Amindu Kumarasinghe, Vinh Bui, Reza Ghanbarzadeh | cs.CV | 2026-11-02 |
| #26 | Do Visual RL Gains Scale at Test Time? A Quantile View of Post-Training | Austin Wang, Lexing Ying | cs.LG | 2026-11-02 |
| #27 | Embedding a de Rham Complex Structure into Eig-PIELM for Maxwell Eigenvalue Problems | Hao Kang, Liang Li, Xing Li | math.NA | 2026-11-02 |
| #28 | Concise-9B: Removing the Slack from a Reasoning Model's Thinking | Alexander Boesgaard Lorup | cs.LG | 2026-11-01 |
| #29 | Iterative Gumbel Planning for Continuous Control | Shaohuai Liu, Weirui Ye, Yilun Du +1 | cs.LG | 2026-11-01 |
| #30 | Restrained Diffusion Bridges: Targeted Denoiser Training and Refinement | Xuanxi Zhang, Kevin S. Cheng, Weizhou Wang +1 | cs.LG | 2026-11-01 |
| #31 | SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training | Ziming Li, Lu Yu, Jiatan Huang +3 | cs.AI | 2026-11-01 |
| #32 | Rare Event Constrained Reinforcement Learning with Large Deviations | Rahul Misra | stat.ML | 2026-11-01 |
| #33 | METER: Matched-Event Calibration for Short-Event EEG Microstate Transition Analysis | Abdul Basit, Eklavya Tomar, Muhammad Shafique | cs.LG | 2026-11-01 |
| #34 | SensOFormer: Foundation Models for Particle Accelerators | Mahindra Rautela, Alexander Scheinker | cs.LG | 2026-11-01 |
| #35 | FinishStrong: Learning to End Well after Imperfect Start in Video Temporal Grounding | Yuda Zou, Boxiang Zhou, Xin Zhou +5 | cs.CV | 2026-11-01 |
| #36 | Wave Physics as Representation: Tensor-Structured Neural Reconstruction for Ocean Acoustic Fields | Yifan Sun, Panqi Chen, Weifeng Shi +2 | cs.LG | 2026-11-01 |
| #37 | Stand-In Effects and Pooling Amplification: Design-Based Tests of Whether Biological World Models Use Actions | Bowen Xu, Boyu Chen | cs.LG | 2026-11-01 |
| #38 | DyRadio: Spatiotemporal Diffusion for Dynamic Radio Map Reconstruction | Zhijie Fan, Zhifeng Zhao, Rongpeng Li | cs.LG | 2026-11-01 |
| #39 | Recoverability-Aware Evaluation of Diffusion Video Inpainting and Object Removal | Yanliang Qi, Jiacheng Ding, Cong Guo +1 | cs.CV | 2026-11-01 |
| #40 | Search-Aware On-Policy Self-Distillation with Sibling Alignment for Generative Recommendation | Rongfeng Guo, Zhuang Zhuang, Ji Dai +6 | cs.LG | 2026-11-01 |
| #41 | Beyond Validation Loss: Coverage and Reliability Dynamics in Robot Policy Pretraining | Zhanyi Sun, Max Simchowitz, Shuran Song | cs.LG | 2026-11-01 |
| #42 | Finite-Time Online Sample Complexity for Conditional Diffusion Models | Mudit Gaur, Prashant Trivedi, Sasidhar Kunapuli +2 | cs.LG | 2026-11-01 |
| #43 | Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching | Mudit Gaur, Prashant Trivedi, Shuchin Aeron +3 | cs.LG | 2026-11-01 |
| #44 | CUFormer: Modality-Aware CT-Ultrasound Point Cloud Registration for Orthopedic Navigation | Lixing Tan, Qing Xia, Yuting Guo +2 | cs.CV | 2026-11-01 |
| #45 | AR-RRG: Anatomy-Guided Retrieval-Driven Radiology Report Generation | Xiang Zhang, Shijie Song, Wanqing Zhao +8 | cs.CV | 2026-11-01 |
| #46 | Improved Sample Complexity Analysis For First Order Bilevel Reinforcement Learning | Mudit Gaur, Naman Saxena, Vaneet Aggarwal | cs.LG | 2026-11-01 |
| #47 | Resolve, Clear, or Defer: Training-Free Active Prototype Triage for Ecological Detection Pipelines | Anirudh Potlapally, Brijesh Nanda Brunda Yogananda, Jianyang Gu +4 | cs.CV | 2026-11-01 |
| #48 | Correctness and Predictive Uncertainty in Bayesian TSK Fuzzy Regression: A Reproducible Evaluation on Tabular and Building-Meter Data | Zhiren Xiao | cs.LG | 2026-11-01 |
| #49 | FOCUS: Closed-Loop Attention Feedback for Efficient Vision-Language Understanding | Akul Santhosh, Aastha Jhunjhunwala | cs.AI | 2026-11-01 |
| #50 | SpecUltra: A Unified Foundation Model for Heterogeneous Spectral Images | Weili Kong, Baisen Liu, Xiaojun Bi +1 | cs.CV | 2026-11-01 |