| 1 | Towards Looped Models Done Right, Part II: Rethinking at Fixed Points | Benhao Huang, Chufan Shi, Junlin Chen +4 | cs.LG | 2026-10-05 |
| 2 | Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model | Sahil Mahendrakar | cs.SD | 2026-10-05 |
| 3 | TAPDreamer: Transferable Adversarial Patches for World Action Models | Xuanyu Lu, Fengqing Jiang, Kaiyuan Zheng +8 | cs.CV | 2026-10-05 |
| #4 | H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning | Wancong Zhang, Basile Terver, Michael Rabbat +2 | cs.LG | 2026-10-05 |
| #5 | A Response Theory Probe for Learned Stochastic AI Simulators, Tested on Lorenz-63 | João Böger, Simon Driscoll, Niccolò Zagli +2 | math.DS | 2026-10-05 |
| #6 | Out-of-control Hamiltonian Learning | Weiyuan Gong, Muzhou Ma, Sitan Chen +2 | quant-ph | 2026-10-05 |
| #7 | Improved Convergence of Large Stepsize Gradient Descent for Logistic Regression | Xiaochuan Gong, Ang Li | cs.LG | 2026-10-05 |
| #8 | RealtimeWAM: One-Step Asynchronous World Action Models | Chengtao Lv, Jinyang Du, Shuyi Feng +7 | cs.CV | 2026-10-05 |
| #9 | Empirical Variational Autoencoder | Kaede Shiohara | cs.LG | 2026-10-05 |
| #10 | NeuroCBIR: A Fast and Accurate Image Retrieval System for Whole-Brain and Region-Specific MRI | Felix Nieto-del-Amor, Jingru Fu, J. -Sebastian Muehlboeck +3 | cs.CV | 2026-10-05 |
| #11 | A Physics-Guided Transformer Framework for Electromigration Analysis in Multi-Segment Interconnects | Pavlos Stoikos, Anuj Pathania, George Floros | cs.LG | 2026-10-05 |
| #12 | FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials | Viktor Zaverkin, Payman Goodarzi, Sergey V. Sukhomlinov +4 | cs.LG | 2026-10-05 |
| #13 | Fine-Tuning a 3B-Parameter LLM on a Smartphone: Characterizing Sustained Training | Andrew Geyko, Marius Mosbach, André Brinkmann | cs.DC | 2026-10-05 |
| #14 | VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action Models | Jaemin Kim, Jiahn Kim, Taesik Gong | cs.RO | 2026-10-05 |
| #15 | DP-ES: Differentially Private Evolution Strategies for Prompt Optimization | Ziniu Liu, Aiping Li, Yue Han +5 | cs.CR | 2026-10-05 |
| #16 | Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning | Lingyu Shen, Wei Tang, Fakhri Karray +1 | cs.CV | 2026-10-05 |
| #17 | APOD: reasoning-guided agentic population ordinary differential equation discovery for pharmacological digital twins | Romain Ferrara, Martin Soucail, Victor Gertner +7 | q-bio.QM | 2026-10-05 |
| #18 | Reinforcement Learning-Based Optimization of Workload-Aware Power Delivery Networks | Oran Hayes, Maria Pantazi-Kypraiou, Athanasios Tziouvaras +4 | cs.AR | 2026-10-05 |
| #19 | ORCA: The Annealed Spectral Conditioning Optimizer for Faster, Better LLM Training | Yuanshi Liu, Boyuan Jiang, Liang Hou +4 | cs.LG | 2026-10-05 |
| #20 | Flash-OPD: Fast On-Policy Distillation | Wei Chen, Junle Chen, Yitong Yang +6 | cs.LG | 2026-10-05 |
| #21 | Rethinking Least-Core Computation in Contextual-Distractor Games | Hiroshi Kera, Toshinori Yamauchi, Sai Ganesh Nagarajan | cs.LG | 2026-10-05 |
| #22 | Polynomial neural surrogates for designing photonic quantum experiments | Rohit Chaurasiya, Xuemei Gu | quant-ph | 2026-10-05 |
| #23 | P3: Persistent Particle Planning for Constrained Diffusion Control | Hikmet Simsir, Mahyar Fardinfar, Ozgur S. Oguz | cs.RO | 2026-10-05 |
| #24 | Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Sampling | Sam McCallum, Niklas Rindtorff, Alexander Tong +1 | cs.LG | 2026-10-05 |
| #25 | StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs | Zhe Wei, Mengqi Guo, Yuan Yuan +3 | cs.LG | 2026-10-05 |
| #26 | Fast Last-Iterate Convergence in Zero-Sum Markov Games with Bandit Feedback | Yuheng Zhang | cs.LG | 2026-10-05 |
| #27 | JLD: Perceptual Distance Through A Jacobian Lens | Shreshth Saini, Balu Adsumilli, Alan C. Bovik | cs.CV | 2026-10-05 |
| #28 | ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning | Seil Kang, Hangoo Kang, Tarun Suresh +4 | cs.LG | 2026-10-05 |
| #29 | TurboPairFormer: Fast and Stable Protein Folding Model Training with an Optimized Triangle Attention Kernel | Yide Ran, Chelsea Lowman, Jan Domański +6 | cs.LG | 2026-10-05 |
| #30 | Dual-Rate Force-Image Control with Model-Based Orientation Limits for Robotic Ultrasound | Tyler Foster, Qiang Zhang, A B M Tahidul Haque +1 | cs.RO | 2026-10-05 |
| #31 | AdaSpark: Adaptive DSpark with Online Learning for Tree Verification and N-gram Fill | Liquan Liu, Yifan Zhang, Bowei Xu | cs.LG | 2026-10-05 |
| #32 | A Three-Dimensional Reverse-Projection Method for Sparse Point Cloud Completion and Its Application to High-Speed Train Nose Reconstruction | Xiaozhen Ma, Zhao Tang, Hanbin Lai +2 | cs.CV | 2026-10-05 |
| #33 | SimpleMark: Fast Multi-Bit Text Watermarking under f -Divergence Constraints | Benjamin D. Kim, Wanrong Zhang, Weitong Ruan +2 | cs.CR | 2026-10-05 |
| #34 | Nexus: An Execution Fabric for AI Agents Across Cloud, Edge, and Devices | Cary Chang, Jialin Zhou | cs.DC | 2026-10-05 |
| #35 | Toward AI Trustworthiness: Finding Analytically Proven Forward-Invariant Sets for AI-Controlled Systems | Haoyang Song, Xikun Yang, Qixin Wang | cs.AI | 2026-10-05 |
| #36 | Square-Root Regret for Adversarial Multiplayer Bandits without Collision Information or Shared Randomness | Chenyu Gan | cs.LG | 2026-10-05 |
| #37 | An LLM-in-the-loop RL Framework for Bioinformatics Feature Selection | Xinyuan Wang, Deepti Agrawal, Yanjie Fu | cs.LG | 2026-10-04 |
| #38 | What Is a Repeated Token Worth? The Scaling Geometry of Multi-Epoch Pretraining | Yekun Chai, Haoyi Xiong | cs.CL | 2026-10-04 |
| #39 | Factoriax: A GPU-Accelerated Factorio-Style Simulator for Reinforcement Learning | Mickey Beurskens, Tristan Tomilin, Thiago D. Simão | cs.AI | 2026-10-04 |
| #40 | Joint Estimation of Common-Slope Decay Rates and Spatial Amplitudes Using Parameterized Nonnegative Matrix Factorization | Jeremy B. Bai, Filip Elvander, Sebastian J. Schlecht | cs.LG | 2026-10-04 |
| #41 | Universality and Convergence of Generative Flows | Leo Brunswic | cs.LG | 2026-10-04 |
| #42 | Universal Test-Time Training | Zefan Cai, Qinzhe Hu, Ziqiao Ma +2 | cs.LG | 2026-10-04 |
| #43 | Efficient Graph Generation via Direct Prediction and Flow Matching | Susie Lu | cs.LG | 2026-10-04 |
| #44 | Rethinking Tabular Foundation Models On Data Streams | Nilesh Verma, Daniel Nowak-Assis, Afonso Lourenço +4 | cs.LG | 2026-10-04 |
| #45 | CT-Miner: Fast and Coarse-Grained Time-Series Pattern Mining via Cartesian Trees | Hyundong Jin, Hyunki Hong, Yo-Sub Han | cs.DS | 2026-10-04 |
| #46 | ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience | Haodong Lu, Dong Gong | cs.LG | 2026-10-04 |
| #47 | Fast Convergence through Distributed Augmentation for Class-Imbalanced Federated Learning | Arathi Nair M, J. Harshan, Anwitaman Datta | cs.LG | 2026-10-04 |
| #48 | Measuring Learned Monotone Temporal Aggregation at Matched Admissibility | Yew Lee Tan | cs.LG | 2026-10-04 |
| #49 | RoMod: Temporal Routing Modulation via Mixture-of-Experts for Video Anomaly Detection | Chao Huang, Pengfei Wei, Benfeng Wang +5 | cs.CV | 2026-10-04 |
| #50 | SearchJev: A Fast and Calibrated System-1 Model for Search Agents | Congfeng Cao, Lipeng Zuo, Konstantinos Papakostas +6 | cs.IR | 2026-10-04 |