| 1 | Adversarial Training for Pixel Diffusion | Xin Lin, Zhifei Zhang, Yuqian Zhou +4 | cs.CV | 2026-09-29 |
| 2 | A Spectral Theory of Distortion in LLM Graph Reconstruction: Sharp Bounds and Empirical Characterization | Jianru Shen | cs.LG | 2026-09-29 |
| 3 | LIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation | Shengxiang Ji, Boyang Wang, Haiyang Xu +9 | cs.CV | 2026-09-29 |
| #4 | AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation | Rishabh Agrawal, Hejie Cui, Shasha Li +2 | cs.AI | 2026-09-29 |
| #5 | GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection | Taufiq Ahmed, Constantino Álvarez Casado, Daniel Herrera Castro +3 | cs.CV | 2026-09-29 |
| #6 | ReCIRC: Rectified Conformal Risk Control | Bruno Marcondes e Resende, Helton Graziadei, Thiago Rodrigo Ramos +1 | stat.ML | 2026-09-29 |
| #7 | Dimensionally consistent surrogate modelling through dimensional analysis and harmonic expansions | Ernest Tarrus, Hector Gisbert | cs.LG | 2026-09-29 |
| #8 | A foundation model for energy and radiation systems built on heterogeneous scientific interfaces | Samrendra Roy, Tapas Tripura, Yoon Pyo Lee +2 | cs.LG | 2026-09-29 |
| #9 | Improving Function Space Flow Matching with Kernel Optimal Transport | Fred Xu, Thomas Markovich, Barbora Barancikova +1 | cs.LG | 2026-09-29 |
| #10 | UserProxyBench: Evaluating LLM User Simulators for Agent Benchmarks and Training | Ashish Jain, Armaan Sandhu | cs.AI | 2026-09-29 |
| #11 | Prompts Live on an Arc: Gaussian Curricula in Fisher--Rao Coordinates for Rollout-Efficient GRPO | Mei Okonkwo, Pixel Nomand, Julian Berg +5 | cs.LG | 2026-09-29 |
| #12 | No Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detection | Jiaheng Guo, Haochen Zhang, Yu-Chao Huang +3 | cs.LG | 2026-09-29 |
| #13 | Topological Coherence for Self-evolving Multi-agent Systems | Sen Zhao, Ruiqi Kong, Zuyu Zhang +4 | cs.AI | 2026-09-29 |
| #14 | Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution | Bingjun Luo, Jialin Guo, Siqi Li | cs.AI | 2026-09-29 |
| #15 | An Efficient Machine Learning Approach for Degradation Forecasting in AEM Water Electrolysis | Marco Veneriano, Ani Gjergji, Sebastiano Bellani +3 | cs.LG | 2026-09-29 |
| #16 | Does Local Video Understanding Transfer Across Encounters? The EgoGears Benchmark | Yuedong Tan, Lei Qi, Yu Liu +13 | cs.CV | 2026-09-29 |
| #17 | Search Dimension in Unlabeled Projection Pursuit: A Scaling Law for Subspace Restriction | Rares Dimitrie Grozavescu, Mark Girolami | cs.LG | 2026-09-29 |
| #18 | Behavioral Capacity Certificates for Quantized Language Models | Arian Eamaz, Mojtaba Soltanalian | cs.LG | 2026-09-29 |
| #19 | Retrieval Capacity of Self-Attention Under Competition | Timur Mudarisov, Mikhail Burtsev, Radu State | cs.CL | 2026-09-29 |
| #20 | ExceptionDrive: A Planning-Oriented Counterfactual Corner-Case Benchmark for Autonomous Driving | Ziyi Luo, Zhe Sun, Yehao Lu +5 | cs.RO | 2026-09-29 |
| #21 | Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR | Doohyuk Jang, Yoonsik Park, Gyouk Chu +2 | cs.LG | 2026-09-29 |
| #22 | It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them | Nagham Omar, Mahmoud Jabarin, Kinan Ibraheem +1 | cs.CL | 2026-09-29 |
| #23 | Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning | Tianhao Qian, Ziming Hong, Chongyang Gao +2 | cs.LG | 2026-09-29 |
| #24 | Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs | Haozhan Tang, Hao Kang, Han Cai +2 | cs.LG | 2026-09-29 |
| #25 | Evaluation Choices Shape Biomedical ML Claims: A Pediatric Pneumonia Benchmark Case Study | Bhanu Prakash Vangala, Sowmya Guda, Latha Peddi +1 | cs.CV | 2026-09-29 |
| #26 | Mixture of Self-Improving Branches For Agent Harness Optimization | Haoyu Dong, Yuhang Zhou, Zihao Lin +6 | cs.AI | 2026-09-29 |
| #27 | DIET: Deletion-response Expert Trimming for Video Diffusion Transformers | Jiachang Zhang, Teng Hu, Bohao Feng +4 | cs.AI | 2026-09-29 |
| #28 | The Geometry of Inference in Transformer Residual Streams | Timur Mudarisov, Mikhail Burtsev, Radu State | cs.CL | 2026-09-29 |
| #29 | Pixel-Level Transformers in Remote Sensing: A Canopy Height Case Study | Sven Ligensa, Jan Pauls, Karsten Schrödter +2 | cs.CV | 2026-09-29 |
| #30 | Challenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation | Serafima Lebedeva, Sumantrak Mukherjee, Ali Arshad Sadal +8 | cs.LG | 2026-09-29 |
| #31 | Planetary Feature Fields are Scalable Earth Representations | Arjun Rao, Sebastian Loeschcke, Anthony Fuller +3 | cs.CV | 2026-09-29 |
| #32 | A Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System | Kelly McConvey, Sajad Ebrahimi, Nima Jamali +10 | cs.CV | 2026-09-29 |
| #33 | Optimizer-dependent training dynamics converge to the same one-third optimal data scaling | Hyunseok Lee, Mihir Basil, Yizhou Liu +1 | cs.LG | 2026-09-29 |
| #34 | Volatility-Clustering Adaptation for Financial Time Series | Manh Nguyen, Minh Hoang Nguyen, Huu Hiep Nguyen +2 | cs.LG | 2026-09-29 |
| #35 | Locating Answer-Correctness Signals in Frozen Large Language Models | Yuansen Liu, Yixuan Tang, Anthony Kum Hoe Tung | cs.AI | 2026-09-29 |
| #36 | Semantic Map Sharing and Capability-Aware Coverage Planning for AI-Native 6G Robotic Coordination | Abdulqader Dhafer, Qi Wang, Zhou Daniel Hao | cs.RO | 2026-09-29 |
| #37 | Nonpreemptive Scheduling While Learning Context-Dependent Service Rates | Wansoo Choi, Seoungbin Bae, Dabeen Lee | cs.LG | 2026-09-29 |
| #38 | Tracing the Evidence: Faithful Token Attribution Through Vision-Language Reasoning | Bowen Yuan, Danny Wang, Ruihong Qiu +2 | cs.CV | 2026-09-29 |
| #39 | Evaluating and Benchmarking the System One Model Jev | Tobias Deußer, Lorenz Sparrenberg, Rafet Sifa | cs.CL | 2026-09-29 |
| #40 | Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model | Van Bach Nguyen, Jörg Schlötterer, Christin Seifer | cs.CV | 2026-09-29 |
| #41 | SPLASH: Switching Parallel Layouts of Attention with Seamless Handoff for LLM Serving | Chuan Liu, Shuoming Zhang, Zhicheng Li +6 | cs.DC | 2026-09-29 |
| #42 | Authority Bias in Language Models: Source Deference and User Agreement Are Not Interchangeable | Abhinav Rajeev Kumar, Paras Chopra | cs.LG | 2026-09-29 |
| #43 | TomoTransformer: Towards a Foundation Model for CT Reconstruction | AmirEhsan Khorashadizadeh, Benjamín Béjar | cs.CV | 2026-09-29 |
| #44 | When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation | Michele Antonazzi, Alejandra C. Hernandez, José Araujo +2 | cs.RO | 2026-09-29 |
| #45 | XU-RS: Explaining Credal Width in Random-Set Language Models | David Achara, Maryam Sultana, Alexander D. Rast +1 | cs.AI | 2026-09-29 |
| #46 | Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection | Yuankun Xie, Xiaoxuan Guo, Xiaopeng Wang +3 | cs.SD | 2026-09-29 |
| #47 | FedSocket: Recipient-Executable Knowledge Exchange for Heterogeneous Multimodal Federated Learning | Xinyuan Zhao | cs.CV | 2026-09-29 |
| #48 | Orthogonal Yet Coupled: Decoupling Geometric Components for Model Merging | Zijing Wang, Yongkang Liu, Mingyang Wang +8 | cs.CL | 2026-09-29 |
| #49 | Why Adaptive Optimizers Underestimate Rare Tokens | Sangsidhya Kar | cs.LG | 2026-09-29 |
| #50 | From Dissonance to Orchestration: Teacher Intervention in On-Policy Distillation | Yuhao Wang, Ruiyang Ren, Yinan Zhang +3 | cs.CL | 2026-09-29 |