| 1 | SplitJEPA: Learning Invariant and Variant Latent Worlds without Reconstruction | Ruijin Hua, Zichuan Liu, Zhuokai Zhao +1 | cs.LG | 2026-10-08 |
| 2 | How Much Audio Is Left In An Embedding? An Inversion Audit Of Audio Encoders | Marios Glytsos, Brian McFee | cs.SD | 2026-10-08 |
| 3 | ISBO: Scalable Spatio-Temporal Bayesian Optimization with Log Gaussian Cox Process Models via the INLA-SPDE Approach | Kaichuang Yang, Håvard Rue, Jakob Zeitler | stat.ML | 2026-10-08 |
| #4 | MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation | Chenghao Jia, Mengdi Liu, Hong Chang +2 | physics.chem-ph | 2026-10-08 |
| #5 | Efficient and Generalizable Archetypal Analysis for Discrete Data | A. Emilie J. Wedenborg, Jesper Løve Hinrich, Morten Mørup | stat.ML | 2026-10-08 |
| #6 | CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encoding | Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Deyuan Qu +6 | cs.RO | 2026-10-08 |
| #7 | Reliability-Aware Future Conditioning for Temporally Robust Robot Manipulation | Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Zhiyuan Gao +8 | cs.RO | 2026-10-08 |
| #8 | Score-Based Learning of Cluster DAGs from Interventions | Gaetano Tedesco, Alex Markham | stat.ML | 2026-10-08 |
| #9 | Does Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive Encoders | Tao Yang, Jianying Zhou | cs.CV | 2026-10-08 |
| #10 | Neural Decoding as Cognitive Inference | Yi Guo, Changhong Jing, Yong Hu +4 | q-bio.NC | 2026-10-08 |
| #11 | Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning | Xunlei Chen, Qinghui Gong, Jingkun Xue +3 | cs.CL | 2026-10-08 |
| #12 | Learning structured linear dynamical systems from missing observations | Aravinda Kanchana Ruwanpathirana, Hemant Tyagi, Sunny G. W. Wang | stat.ML | 2026-10-08 |
| #13 | Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement | Jingyi Pan, Dan Xu, Qiong Luo | cs.CV | 2026-10-08 |
| #14 | Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing | Jing Ma, Yujia Wu, Zhaoqiang Liu | cs.LG | 2026-10-08 |
| #15 | Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation | Haitong Jiang, Chunlin Liu, Sihan Tang +3 | cs.CL | 2026-10-08 |
| #16 | HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution | Ziying Li, Shengchu Zhao, Huiang He +21 | cs.CV | 2026-10-08 |
| #17 | Hankel Subspace Self-Supervised Learning for Parallel MRI Reconstruction | Mingyu Hu, Siquan Zhu, Xijun Zhong +1 | cs.CV | 2026-10-08 |
| #18 | Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper | Masaaki Nakatsu, Reno Wang | cs.CL | 2026-10-08 |
| #19 | Rare Gate Disagreements Can Limit Plasticity: When Gradient Flow Mispredicts Finite-Batch SGD | Ruoyu Zhao, Mingxuan Zhang, Jianbo Dai +3 | cs.LG | 2026-10-08 |
| #20 | Feature Space Adaptation for Effortless Gaussian Process Flows | Thomas Cowperthwaite, Louis Sharrock, Lachlan Astfalck +1 | stat.ML | 2026-10-08 |
| #21 | RISR: Residual-Informed Scientific Equation Discovery with Large Language Models | Haobo Li, Wenshuo Zhang, Wenxiao Zhao +6 | cs.SC | 2026-10-08 |
| #22 | ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery | Houcheng Jiang, Mao Zheng, Mingyang Song +4 | cs.CL | 2026-10-08 |
| #23 | Finsler Flow Matching: Dynamics-Aware Geodesic Interpolation for Single-Snapshot Trajectory Inference | Niklas Canova, Jonas Simon Fleck | cs.AI | 2026-10-08 |
| #24 | BeliefScope: Diagnosing Evidence-Driven Revision and Pressure-Induced Shifts in Large Language Models | Shuai Guo, Yidong Cui | cs.CL | 2026-10-08 |
| #25 | Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals | Lei Zhao, Qichao Zhao, Bowen Zuo +1 | cs.LG | 2026-10-08 |
| #26 | TAP3D: Thermal-Assisted 3D Human Point Clouds | Xie Zhang, Chengxiao Li, Xuan Liu +1 | cs.CV | 2026-10-08 |
| #27 | Improving Image-Based Nutrition Estimation Through Multimodal Food-Item Verification and Recovery | Jingbo Yue, Bruce Coburn, Jinge Ma +2 | cs.CV | 2026-10-08 |
| #28 | Continuous Ground-Truth Construction and a Recovery Policy for Air--Water Robotic Tracking | Jiangong Xiao, Zhe Sun, Kanzhong Yao +5 | cs.CV | 2026-10-08 |
| #29 | Coefficient Calibration as Selection Pressure in Symbolic Regression | Mattia Billa, Veronica Guidetti, Federica Mandreoli | cs.LG | 2026-10-07 |
| #30 | How Many Repeated Pairwise Comparisons Are Needed for Ranking under Heterogeneity? | Shashaank Aiyer, Han Shao | cs.LG | 2026-10-07 |
| #31 | Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery | Chen Xu, Yunqi Li, Binbin Huang +3 | cs.CV | 2026-10-07 |
| #32 | FoldBack: Self-Correcting Masked Generative Policy for Long-Horizon Garment Folding | Lipeng Zhuang, Shiyu Fan, Yingdong Ru +4 | cs.RO | 2026-10-07 |
| #33 | PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs | Linghao Meng, Feng He, Xuan Yang +5 | cs.CL | 2026-10-07 |
| #34 | CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution | Jixuan Chen, Jiaxin Zhang, Qinyuan Ye +11 | cs.CL | 2026-10-07 |
| #35 | Executing Causal Structure Learning with Linear-Attention Transformers | Amartya Roy, Sayar Karmakar | cs.LG | 2026-10-07 |
| #36 | SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing | Hui Zhang, Yachao Yuan, Jiayun Wang +3 | cs.CR | 2026-10-07 |
| #37 | Beyond the Ergodic Wall: A Discrete Geometric Physics Sandbox for Analysing AI Scaling Limits and Complexity Collapse | Simon Richard Daniel | cs.LG | 2026-10-07 |
| #38 | Finite-Sample Approximation of Hessian-Guided Perturbed Wasserstein Gradient Flows | Ryotaro Kawata, Atsushi Nitanda, Taiji Suzuki | cs.LG | 2026-10-07 |
| #39 | How to train your model organism | Xilin Wang, David Bau, Byron C. Wallace | cs.LG | 2026-10-07 |
| #40 | VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation | Zhuo Chen, Yihua Cheng, Aleš Leonardis +1 | cs.CV | 2026-10-07 |
| #41 | BagDINO: Multi-View Baggage Re-Identification with DINOv3 | Vita Santa Barletta, Danilo Caivano, Rebecca Margiotta +2 | cs.CV | 2026-10-07 |
| #42 | Speaking the Navigator's Language: Trajectory-Grounded Instruction Translation for Frozen Aerial VLN Agents | Xi Chen, Zhe Liu, Xiaogang Xu +8 | cs.AI | 2026-10-07 |
| #43 | Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents | Obada Kraishan | cs.AI | 2026-10-07 |
| #44 | Force without transmission: a depth-induced rank collapse that no loss on the representation reopens | Martin Hofmann, Patrick Mäder | cs.LG | 2026-10-07 |
| #45 | Identifiability of a dissipative knowledge-dynamics model: exact recovery under designed excitation, degeneration on observational data | Arman Kostanian, Armen Beklaryan | cs.LG | 2026-10-07 |
| #46 | AdaPS-LiNGAM: Adaptive Predecessor Selection for Linear Non-Gaussian Acyclic Models under Small-Sample Settings | Shun Yanashima, Kentaro Kanamori, Hirofumi Suzuki | cs.LG | 2026-10-07 |
| #47 | The Silhouette Operator: Identifiability of Low-Rank Measures from One-Dimensional Projections | Robert A. Vandermeulen | math.ST | 2026-10-07 |
| #48 | Identity-Duplication Auditing in National-Scale Neuroimaging Repositories | Jiheng Li, Michael E. Kim, Trent M. Schwartz +19 | cs.CV | 2026-10-07 |
| #49 | MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking | Qilin Zhou, Zhengyuan Wei, Haipeng Wang +3 | cs.CR | 2026-10-07 |
| #50 | Reliability of LLM Judges for Evaluating Entity Alignment | Vaibhava Lakshmi Ravideshik, Mayank Kejriwal | cs.AI | 2026-10-07 |