| 1 | Counting on Dummies: Privacy Amplification with Observable Counts and Truncated Batches | Vitaly Feldman, Audra McMillan, Kunal Talwar | cs.LG | 2026-10-30 |
| 2 | Gradient Descent on Two ReLU Neurons: Global Landscape and Bifurcation Dynamics | Binghua Li, Mengzhe Li, Denny Wu +1 | cs.LG | 2026-10-30 |
| 3 | Exact Theory and Optimal Stepsizes for Stochastic Gradient Descent in Smooth Convex Minimization | Benjamin Grimmer, Qining Shen | math.OC | 2026-10-30 |
| #4 | Prune Gradually, Adapt Sparsely: Efficient Pruning of Large Language Models at Extreme Sparsity | Jean Lucien Randrianantenaina, Hung Nguyen, Nasib Ullah +4 | cs.AI | 2026-10-30 |
| #5 | WASABI: Wasserstein Sampling via Bridge Interpolants | Sebastian Salazar, Dilum Fernando, Michal Kucer +3 | stat.ML | 2026-10-30 |
| #6 | Optimizing Stochastic Policy Geometry for Few-Step Flow Reinforcement Learning | Zhuguanyu Wu, Congjia Chen, Ruihao Gong +4 | cs.AI | 2026-10-30 |
| #7 | Variance Reduction for Decentralized Stochastic Optimization with Multiple Local Updates | Jie Liu, Nicola Bastianello, Wenying Xu +1 | math.OC | 2026-10-30 |
| #8 | Trainable Vector Quantization for Large Language Models | Anastasiia Prutianova, Alina Bogdanova, Mikhail Shutov +3 | cs.LG | 2026-10-30 |
| #9 | Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings | Eunchan Kim, Inwhee Joe | cs.CL | 2026-10-30 |
| #10 | TSBPO: Tree-Structured Branching for Policy Optimization in Interactive Language Agents | Rui Yu, Chong Mu, Jinchuan Zhang | cs.AI | 2026-10-30 |
| #11 | OT-CAL: Optimal-Transport-Guided Adaptive Sample Selection for Efficient Visual Learning | Suryansh Talukdar, Jin Soung Yoo | cs.CV | 2026-10-30 |
| #12 | $\nabla$Mimic: Ultra-Efficient Humanoid Control with Differentiable Simulation | Weyl Lu, Yubei Chen | cs.RO | 2026-10-30 |
| #13 | On the Generation Order in GFlowNets | Timofei Gritsaev, Evgeny Katasonov, Ildus Sadrtdinov +2 | cs.LG | 2026-10-30 |
| #14 | GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning | Chanseul Cho, Noori Bae, Dongheon Lee +1 | cs.CV | 2026-10-30 |
| #15 | FOCUS: First-Order Control Using Optimal Transport Supervision for Imitation from Observations | João A. Cândido Ramos, Lionel Blondé, Hugues Vinzant +2 | cs.LG | 2026-10-30 |
| #16 | Infinite ResNets are Gaussian Mean ODEs | Louis-Pierre Chaintron, Lénaïc Chizat, Javier Maass | cs.LG | 2026-10-30 |
| #17 | Anomalies as Residuals: Cauchy Displacement Networks | Yang Cao, Zihao Guo | cs.LG | 2026-10-30 |
| #18 | Riemannian Optimization on Unknown Manifolds via Stochastic Proximal Refinement | Ruixiang Wu, Jiahao Ai, Tinko Sebastian Bartels +5 | eess.SY | 2026-10-30 |
| #19 | LEAP: Efficient LLM Inference Scheduling with Generalizable Length Prediction | Kwan Yan, Jialun Zhong, Yanzeng Li | cs.AI | 2026-10-30 |
| #20 | rl_rob: A transparent, from-scratch Python library for teaching reinforcement learning from tabular methods to deep policy gradients | Abdulrahman Altahhan | cs.LG | 2026-10-30 |
| #21 | General Frequency Principle for Linear Approximation Classes | Yujun Wang, Yiqi Gu | cs.LG | 2026-10-30 |
| #22 | MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation | Aryan Das, Vinay Kumar Verma, Aakansha Mishra | cs.LG | 2026-10-30 |
| #23 | Elucidating the Design Space of LM Data Attribution | Steven Yu, Sheng-Yu Wang, Kimia Hamidieh +2 | cs.CL | 2026-10-29 |
| #24 | Numerical Integration on Bounded Domains via Learned Reflected Diffusions | Kirill Korolev, Artur Goldman, Timofei Gritsaev +2 | cs.LG | 2026-10-29 |
| #25 | The Precision Wall: An Optimizer-Dependent Boundary for Optimization under Power-Law Measurement Spectra | Lngel Kyo | cs.LG | 2026-10-29 |
| #26 | Preserving Utility in Continual LLM Unlearning via Orthogonal Projections | Juan Belieni, Ana Carolina Erthal, Eliezer de Souza da Silva +1 | cs.LG | 2026-10-29 |
| #27 | Multistep and Multivariate Time Series Explainability with GradientSHAP: A Wind Power Case Study | Robbie Southam, Zhong Fan, Ke Li | cs.AI | 2026-10-29 |
| #28 | Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR | Lang Chen, Zongxin Xu, Borui Wang +2 | cs.AI | 2026-10-29 |
| #29 | Understanding axial attention in TSFMs through single location regression | Andrei-Tiberiu Pantea, Aymeric Dieuleveut | stat.ML | 2026-10-29 |
| #30 | D-MOD: Diffusion mode estimation for accelerated MRI | Md Kawsar Ahmed, Mathews Jacob | cs.LG | 2026-10-29 |
| #31 | FIDE: Fiber-Informed Differentiable Experimental Design for Reference-Relative Law Dynamics | Pietro Zanotta, Ján Drgoňa | cs.LG | 2026-10-29 |
| #32 | When to spend privacy: optimal allocation in private learning | Umberto Biccari, Yongcun Song | cs.LG | 2026-10-29 |
| #33 | Low-Bit GDN Recurrent-State Quantization: Global Gradient-aware Allocation and Pure-Write Sliding Windows | Qinghang Huang, Xuchu Huang, Xunzhao Yin | cs.LG | 2026-10-29 |
| #34 | TokenRepel: Generating Diverse Image Sets Without Compromising Quality | Qingtao Yu, Zhen Wang, Ning Lai +3 | cs.CV | 2026-10-29 |
| #35 | CovFedAvg: Local Low-Loss Curves and Federated Model Selection | Federico Lucchetti, Marcus Völp | cs.LG | 2026-10-29 |
| #36 | sDMD: Sinkhorn Distribution Matching Distillation | Jaihoon Kim, Lingxiao Li, Soshi Shimada +3 | cs.CV | 2026-10-29 |
| #37 | LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models | Alexandros Gkillas, Ioulia Kapsali, Christos Anagnostopoulos +1 | cs.CV | 2026-10-29 |
| #38 | Revisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective | Chao Chen, Pengyang Shao, Wei Qin +3 | cs.AI | 2026-10-29 |
| #39 | Implicit Bias of (Stochastic) Gradient Descent on Deep Linear Diagonal Networks | Wiebke Bartolomaeus, Holger Rauhut | cs.LG | 2026-10-29 |
| #40 | Adaptive Federated Optimization Across Smooth and Nonsmooth Regimes | Zimeng Wang, Ali Dadras, Alp Yurtsever | math.OC | 2026-10-29 |
| #41 | Operator-Aware Posterior Sampling for Multivariate Weather Downscaling | Carlo Saccardi, Rudolf Saathof, Geethu Joseph +1 | cs.CV | 2026-10-29 |
| #42 | Conic-Lifting for Learning-rate-free Convex Optimization | Julien Grand-Clément, Joon Kwon, Francesco Orabona | math.OC | 2026-10-29 |
| #43 | Last-Iterate Convergence for Constrained MDPs: From Dual Descent to Primal-Dual | Michael Lu, Max Qiushi Lin, Mo Chen +1 | cs.LG | 2026-10-29 |
| #44 | Agent-Wise Test-Time Normalization for Camera-Based Cooperative Perception with Corrupted Collaborators | Yu Wang, Shaohua Wang, Yicheng Li +1 | cs.CV | 2026-10-29 |
| #45 | Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection | Muhammad Uzair Shahid, Muhammad Zabil Mehboob | cs.AI | 2026-10-29 |
| #46 | Sparse Fine-Tuning for Parameter-Efficient Adversarial Training | Zhaoxin Wang, Zihang Ding, Handing Wang | cs.LG | 2026-10-29 |
| #47 | Softmax Routing Dynamics in Mixture-of-Experts Models: Collapse and Recovery | Shengze Xu, Maolin Deng, Tieyong Zeng | cs.LG | 2026-10-29 |
| #48 | ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting | Houqiang Zhong, Tianchi Zhu, Qiang Hu +3 | cs.CV | 2026-10-29 |
| #49 | Class-aware Latent Attention Replay (CLAR): Class Incremental Hazard Diagnosis for Resilient AI in the Manufacturing Industrial Internet | Avranshu Mahanty, Ran Jin, Yingyan Zeng | cs.LG | 2026-10-29 |
| #50 | IMRouter: Imbalance-aware Temporal Pattern Routing for LLM-based Time Series Forecasting | Xin Yang, Cai Xu, Haishun Chen +4 | cs.LG | 2026-10-29 |