| 1 | UE5M3 FP4 Block Scaling for Stable Language Model Pretraining | Robert Hu, Carlo Luschi, Paul Balanca | cs.LG | 2026-09-02 |
| 2 | Learning Spectral-Like Mesh-Free Discretisations | Lucas Gerken Starepravo, Henry Broadley, Steven Lind +1 | physics.comp-ph | 2026-09-02 |
| 3 | Dutch Books for Language Models | Isaiah Andrews, Suproteem Sarkar | econ.GN | 2026-09-02 |
| #4 | Full-Model Optimality for Tunable Linear Generative Priors in Compressed Sensing | Zhaoming Li, Paul Hand | stat.ML | 2026-09-02 |
| #5 | Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents | Vasileios Rizeakos, Georgios Paisios, Alexandros Machairas +2 | cs.AI | 2026-09-02 |
| #6 | Neural operators approximate strongly continuous convex monotone semigroups | Jonas Blessing, Philipp Schmocker, Alessandro Sgarabottolo | math.NA | 2026-09-02 |
| #7 | Dimension Dependent Correlation Gap Bounds under Restricted Independence | Arjun Ramachandra | math.PR | 2026-09-02 |
| #8 | Spatially Aware World Action Model via Geometric Latent Diffusion | Javier Alejandro Lopetegui Gonzalez, Paul Pacaud, Cordelia Schmid | cs.CV | 2026-09-02 |
| #9 | The Diagnosis a Reporter Leaves Unspoken: Surfacing Frozen Tumor Features for Brain-Tumor MRI Reporting | Khawaja Murad ul Hassan, Ruqiyya Adil, Adil Qayyum +4 | cs.CV | 2026-09-02 |
| #10 | Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts | Kirill Labzin, Stepan Kulibaba, Artem Dzhalilov +1 | cs.LG | 2026-09-02 |
| #11 | Poisoning Attacks on the PGM-index | Atsuki Sato, Martin Aumüller, Yusuke Matsui | cs.DB | 2026-09-02 |
| #12 | Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL | Hyeonseong Jeon, Youngwoon Lee | cs.LG | 2026-09-02 |
| #13 | Signal or Noise? Auditing Rotation-Induced Saliency Drift in Medical and Aerial Imaging | Khawaja Murad ul Hassan, Mehran Ebrahimi | cs.CV | 2026-09-02 |
| #14 | Learning the Constitutive Behavior of Materials via Neural Operators and Causal Attention: Case Studies in Plasticity and Damage | Rishabh Arora, Lisa Scheunemann, Tim Brepols +1 | cs.LG | 2026-09-02 |
| #15 | Exact Limits of Random Projections for Preserving Geometry: Distance Recovery, Nearest-Neighbor Rankings, and Covariance Shape in Gaussian Models | Piyush Sao | cs.LG | 2026-09-02 |
| #16 | Online Non-Monotone DR-Submodular Maximization Matching the Offline $0.401$ Factor | Vaneet Aggarwal, Yiyang Lu | cs.LG | 2026-09-02 |
| #17 | A Power Law in Logarithm's Clothing: On the Scalability of Graph-Based Vector Search | Sajad Faghfoor Maghrebi, Navid Eslami, Niv Dayan | cs.DB | 2026-09-02 |
| #18 | MeanField Surrogate Modeling for Scalable Runtime Scheduling of Concurrent Heterogeneous AI Inference on Shared GPUs | Youssef Ennouri, Soonhoi Ha | cs.DC | 2026-09-02 |
| #19 | The Dynamics of Continuous Mixture Collapse in Language Models | Ali Backour | cs.LG | 2026-09-02 |
| #20 | HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models | Renjie Xie, Juncheng Yang, Aoting Hu +4 | cs.AI | 2026-09-02 |
| #21 | Perceptually Regularized Diffusion Model for Image Super-Resolution | Chuxiangbo Wang, Pavithra Venkatachalapathy, Ying Liang +4 | eess.IV | 2026-09-02 |
| #22 | 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 |
| #23 | Posterior Tempering Explains Variance Inflation in Linear and Generalized Linear Thompson Sampling | Prateek Jaiswal, Debdeep Pati, Anirban Bhattacharya +1 | stat.ML | 2026-09-02 |
| #24 | Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation | Akio Hayakawa, Yusuke Mukuta, Tatsuya Harada | cs.CV | 2026-09-02 |
| #25 | CAHR-Net: Condition-Adaptive Hysteresis Reconstruction for Compact and Interpretable Magnetic Core Loss Modeling | Chunye Gong, Cong Yao | cs.LG | 2026-09-02 |
| #26 | Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and Deployment | Anirudh Malik, M Sparsh Mehra, Poojith Devan | cs.AI | 2026-09-02 |
| #27 | OR-Transformer: Scaling Real-Time Decision-Making to 1,000 Items | Shuze Daniel Liu, David Simchi-Levi, Claire Chen +2 | cs.LG | 2026-09-01 |
| #28 | Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence? | Wenlong Wang, Fergal Reid | cs.AI | 2026-09-01 |
| #29 | HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation | Alessandro Zirilli, Davide Marincione, Evgenios M. Kornaropoulos +2 | cs.CR | 2026-09-01 |
| #30 | RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basis | Amirhosein Azarpour | cs.LG | 2026-09-01 |
| #31 | What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models | Sharon S. Musa, Fereshteh Forghani, Harrish Thasarathan +3 | cs.CV | 2026-09-01 |
| #32 | A Mathematical Theory of Reusable Neural Bases for Network Compression | Binshuai Wang | cs.LG | 2026-09-01 |
| #33 | Benchmarking Spatial, Spectral, and Self-Supervised Cues for Face Forgery Detection under Realistic Degradation | Lucas Cunha, Lucas Sotomaior, Lucas Gasperin +3 | cs.CV | 2026-09-01 |
| #34 | Optimizing Byzantine Node Placement in Decentralized Federated Learning | Edoardo Gabrielli, Gabriele Tolomei | cs.LG | 2026-09-01 |
| #35 | Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications | S. Sifaoui, E. Angelini, S. Toupin +2 | cs.CV | 2026-09-01 |
| #36 | Investigating Linear Probe Robustness to Linguistic Register, Medical Specialty, and Corpus Shifts in Medical QA | Nishant Mishra, Ameen Abu-Hanna, Iacer Calixto | cs.CL | 2026-09-01 |
| #37 | Matched Queries for Curvature and Density at Branching Junctions | Ziqi Zhao, Qingjian Ni | stat.ML | 2026-09-01 |
| #38 | MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval | Debanjan Mahata, Atharva Tendle, Daniel Preotiuc-Pietro +2 | cs.IR | 2026-09-01 |
| #39 | HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives | Sathiyamohan Nishankar, Pubudu Sanjeewani, Asanka Perera +1 | cs.CV | 2026-09-01 |
| #40 | Dual Process Motion Planning | Jiayi Yan, Francesco Fabiano, Alessandro Abate | cs.AI | 2026-09-01 |
| #41 | H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning | Jia Ling, Yangfan Wang, Chen Tang +4 | cs.AI | 2026-09-01 |
| #42 | Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening | Zhilong Song, Lixue Cheng | cond-mat.mtrl-sci | 2026-09-01 |
| #43 | When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP | Shota Sato, Hajime Kiyama, Tosho Hirasawa +1 | cs.CL | 2026-09-01 |
| #44 | Neural Symbollic Regression Using Deep Learning and Sparse Modelling | Ravi Kumar U, Sumitra S | cs.LG | 2026-09-01 |
| #45 | Accelerating Reinforcement Learning via MPC Solver-Gradient Guidance for Weights-varying MPC | Baha Zarrouki, Arslan Thobani, Jasper Hoffmann +6 | cs.RO | 2026-09-01 |
| #46 | Lagged Coupling: Internal Representations Become Readable Before They Become Causal | Xining Xun | cs.CL | 2026-09-01 |
| #47 | iPINN for Broadband CARS Phase Retrieval: A Framework for Function Approximation and Inverse Modeling Problems in Nonlinear Spectroscopy | Ravi Teja Vulchi, Carl Messerschmidt, Mohammadsadegh Vafaeinezhad +4 | cs.LG | 2026-09-01 |
| #48 | The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence | Genpei Zhang | cs.CV | 2026-09-01 |
| #49 | MemoryWalker: Stop Training Agents on Contexts They Never Saw | Zinco J, Xunjie Zhu, Shen Huang +3 | cs.LG | 2026-09-01 |
| #50 | Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents | Haoyang Chen, Yi Liu, Jianzhi Shao +3 | cs.AI | 2026-09-01 |