| 1 | Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks | Shivang Rawat, Mirko Morello, Flaviano Morone +1 | cs.LG | 2026-09-03 |
| 2 | Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM | Sergii Kozyrev, Davyd Maiboroda | cs.AI | 2026-09-03 |
| 3 | Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving | Ruoyu Yao, Yusen Xie, Qingzhao Liu +5 | cs.CV | 2026-09-03 |
| #4 | Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing | Kubilay Kağan Kömürcü, İlkay Öksüz | cs.CV | 2026-09-03 |
| #5 | RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting | Yuchen He, Yueyang Cang, Zhiyuan Ning +2 | cs.LG | 2026-09-03 |
| #6 | Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting | Muneeb Khan, Frederic Kirstein, Terry Ruas +1 | cs.AI | 2026-09-03 |
| #7 | FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation | Yutian Zhang, Siyuan Ma, Liwen Yang +6 | cs.RO | 2026-09-03 |
| #8 | Xiaomi-TabLDM: A Tabular Foundation Model Technical Report | Xiaomi-TabLDM Team, :, Penghui Wang +10 | cs.AI | 2026-09-03 |
| #9 | GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History | Yaozheng Xia, Zaiping Zhu, Bo Pang +4 | cs.HC | 2026-09-03 |
| #10 | From Ordered Bernoulli Levels to Critical-Line Geometry: Integer Quantization, Bernoulli Residual Phase, and Prime-Power Spectra | Y. Kenan Yılmaz | cs.LG | 2026-09-03 |
| #11 | Observation-Conditioned Latent Energy Priors for Sparse Implicit Neural Shape Completion | Paul Büschl, Ezequiel de la Rosa, Julia Wolleb +3 | cs.CV | 2026-09-03 |
| #12 | ToPO: Token-Conditioned Preference Routing for Attention-Based Latent Diffusion Models | Juntao Xu, Shihong Li, Hoi Fan Au +1 | cs.CV | 2026-09-03 |
| #13 | Relative Prime Factorization and Finite-State Presentations under Fixed Finite-Monoid Observation | Takayuki Kuriyama | cs.FL | 2026-09-03 |
| #14 | Residual neural networks overcome the curse of dimensionality for semilinear heat equations | Ilkhom Mukhammadiev, Diyora Salimova | math.NA | 2026-09-03 |
| #15 | Correlated initialization of deep residual networks | Felix Benning, Ivan Nourdin, Giovanni Peccati | math.PR | 2026-09-03 |
| #16 | Coupled Scaling: A Representational Accessibility Framework for Neural Scaling Laws | Jie Wang | cs.LG | 2026-09-03 |
| #17 | Residual Optimal Transport-Based Experts Collaboration Towards Modality-Aware Infrared-Visible Object Detection | Yue Zhao, Hua Yu, Yukun Zhao +6 | cs.CV | 2026-09-03 |
| #18 | Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations | Karthika Nhayakkat, Rajat Verma, Maharaj Brahma +4 | cs.CL | 2026-09-03 |
| #19 | Towards a Statistical Understanding of Mixture-of-Experts | Siyuan He, Bokai Yang, Jie Hu +2 | stat.ML | 2026-09-03 |
| #20 | Preprocessing Failure and Adversarial Detection in Depthwise-Separable Edge Vision Systems | Jannatul Masruk Mukta, Rifa Sanjida, Adrita Rahman Tory +2 | cs.CV | 2026-09-03 |
| #21 | It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories | Yigit Utku Bulut | cs.LG | 2026-09-03 |
| #22 | Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models | Ross Tieman, Evan Markou | cs.LG | 2026-09-03 |
| #23 | Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface | Adrita Rahman Tory, ABM Shawkat Ali, Md Abu Layek +1 | cs.CR | 2026-09-03 |
| #24 | Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting Training | Yixiong Yang, Sisheng Zhang, Qingsong Yan +2 | cs.CV | 2026-09-03 |
| #25 | Selective Hypergraph Refinement for Frozen Graph Clustering | Zimo Si | cs.LG | 2026-09-03 |
| #26 | Distilling deep optical flow stereo methods to retrieve dense three-dimensional wind fields | Thomas J. Vandal, Dong L. Wu, James L. Carr +5 | cs.LG | 2026-09-02 |
| #27 | Mesh-Native Physics-Informed Graph Surrogates for TCAD-in-the-Loop Design Space Exploration | Leonid Popryho, Ayoub Sadeghi, Inna Partin-Vaisband | cs.LG | 2026-09-02 |
| #28 | A Top-Down Framework for Metric-Scale Athlete Localization from Single Broadcast Frames | Thanh-Khoi Nguyen, Hoang-Phuc Nguyen, Linh-Huynh +1 | cs.CV | 2026-09-02 |
| #29 | oHC: Orthogonal Hyper-Connections on SO(4) via Quaternions | Haoqiang Guo, Xuyi Chen, Bo Ke +5 | cs.CL | 2026-09-02 |
| #30 | Generalizable Brain Tumor Segmentation with Self-Training and Tumor-Aware Deformations | Henrique Zan Grande, Jeovane Honorio Alves, Rayson Laroca +1 | cs.CV | 2026-09-02 |
| #31 | RINSE: Robust Target-Time Normality Estimation for Zero-Shot Graph Anomaly Detection | Taufikur Rahman Fuad, Md Abrar Jahin, Amir Hussain | cs.LG | 2026-09-02 |
| #32 | IFW-BLS: Dual-Robust Broad Learning System with Intuitionistic Fuzzy Wave Loss | Mushir Akhtar, M. Tanveer | cs.LG | 2026-09-02 |
| #33 | Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts | Kirill Labzin, Stepan Kulibaba, Artem Dzhalilov +1 | cs.LG | 2026-09-02 |
| #34 | Diffusion-Encoding Gaussian Field for Joint k-q dMRI Reconstruction | Zhibo Chen, Yajuan Huang, Yu Guan +3 | cs.CV | 2026-09-02 |
| #35 | When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization | Haozhang Li, Yangguang Shao, Xinjie Lin +3 | cs.CR | 2026-09-02 |
| #36 | CC-4DGS: Computational Deformation and Point-Cloud Compression for Storage-Efficient Dynamic Gaussian Splatting | Kyungdae Park, Chae Eun Rhee | cs.CV | 2026-09-02 |
| #37 | GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories | Arpita Joshi | cs.LG | 2026-09-02 |
| #38 | Online Non-Monotone DR-Submodular Maximization Matching the Offline $0.401$ Factor | Vaneet Aggarwal, Yiyang Lu | cs.LG | 2026-09-02 |
| #39 | A Computational Comparison of Fourier Spectral Differentiation and Spatial Automatic Differentiation in Periodic Physics-Informed Neural Networks | Xilai Liang, Zhao Zhang | cs.LG | 2026-09-02 |
| #40 | KSG-Net: Key-Sparse and Global-Context Learning for Maritime 3D Ship Detection | Zhouyuan Huai, Meiqi Wan, Yan Yang +4 | cs.CV | 2026-09-02 |
| #41 | Modeling What Changes: Sparse, Residual World Models for Object-Centric Manipulation | Param Thakkar, Parsika Paresh Shah, Manisha Sushant Gote | cs.RO | 2026-09-02 |
| #42 | HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models | Renjie Xie, Juncheng Yang, Aoting Hu +4 | cs.AI | 2026-09-02 |
| #43 | How Output Format Confounds Data Quality and Capability in Instruction Tuning | Chengguang Gan, Hanjun Wei, Yunhao Liang +3 | cs.CL | 2026-09-02 |
| #44 | Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation | Wenhui Chen, Zhifeng Li, Jie Zhou +5 | cs.LG | 2026-09-02 |
| #45 | Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis | Yagna Manasa Boyapati, Chong Yu, Tianyu Jiang +1 | cs.CR | 2026-09-01 |
| #46 | Interpretable Symptom Vectors for Depression in a Large Language Model | Fangyi Zhu, Ajay Subramanian, Allison Constant +3 | cs.CL | 2026-09-01 |
| #47 | When Does Information Sharing Improve Decentralized Discovery? Aggregation, Independent Rescue, and Equilibrium Selection | Yohei Nakajima | cs.AI | 2026-09-01 |
| #48 | Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation | Himil Vasava, Ming Jiang | cs.CL | 2026-09-01 |
| #49 | The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally | Jundong Hu, Shekar Ramachandran | cs.LG | 2026-09-01 |
| #50 | Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks | Jing Xiao, Xinhai Chen, Qinglin Wang +5 | cs.LG | 2026-09-01 |