| 1 | Searching for New Physics with Reinforcement Learning | Jacky Kumar, Marianne Bouchard, David London | hep-ph | 2026-09-09 |
| 2 | Decoupled Self-Forcing Distillation for Streaming Talking Head Generation | Yanru An, Ruiyan Wang, Wenwu Wei +7 | cs.CV | 2026-09-09 |
| 3 | Training Trajectories Determine Circuit Removability in Annealable Soft-Prior Transformers | Zonglin Yang, Ziming Zhao, Wei Tang +5 | cs.LG | 2026-09-09 |
| #4 | When Fusion Fails: Corruption-Aware Rebalanced Fusion for Multi-Modal Medical Image Segmentation | Yuchen Pei, Xiaoyu Hu, Yixiong Zou +5 | cs.CV | 2026-09-09 |
| #5 | DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs | Bhuvan Arora, Devesh Saraogi, Sravya Varada +1 | cs.CL | 2026-09-09 |
| #6 | Hierarchical and Permutation-Invariant Feature Transformation Learning via Policy-Guided Embedding Search | Rui Liu, Tao Zhe, Yanyong Huang +5 | cs.LG | 2026-09-09 |
| #7 | Are You Learning Biological Signal or Shortcuts? Auditing and Mitigating Bias in Protein-Protein Interaction Datasets | Judith Bernett, Anton Spannagl, Joel Ås +2 | q-bio.MN | 2026-09-09 |
| #8 | CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization | Luyao Tang, Jiewei Zheng, Kunze Huang +3 | cs.LG | 2026-09-09 |
| #9 | From Retrieval to Weights: Parametric Individualization of Small Language Models with Individual Text Corpora | Christoph Wigbels, Ali Abusaleh, Markus T. Jansen +2 | cs.CL | 2026-09-09 |
| #10 | RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases | Yingqian Wu, Jingcong Liang, Siyuan Wang +4 | cs.AI | 2026-09-09 |
| #11 | A statistical approach to bias in zero-shot learning: the lens of handwriting recognition | Clarence Chew, Gim Siang Chia, Sukalpa Chanda +2 | stat.ML | 2026-09-09 |
| #12 | Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States | Marek Jeliński, Jan Dubiński, Maciej Chrabaszcz +1 | cs.AI | 2026-09-09 |
| #13 | Dynamical Non-compensatory Multidimensional IRT Model Using Variational Approximation | Hiroshi Tamano, Daichi Mochihashi | stat.ME | 2026-09-09 |
| #14 | Optimal Value Inference for Reinforcement Learning | Nan Lu, Ethan Lee, James M. Robins +2 | stat.ML | 2026-09-09 |
| #15 | Deep and shallow biases in language models | An Vo, Vy Tuong Dang, Khai-Nguyen Nguyen +4 | cs.CL | 2026-09-09 |
| #16 | Strangers to Themselves: What Language Models Say About Themselves Is Generic | Phil Blandfort, Urja Pawar | cs.LG | 2026-09-09 |
| #17 | When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors | Cho-Ying Wu | cs.CL | 2026-09-09 |
| #18 | LogiScope-VQA: Benchmarking Vision-Language Models for Logistics Hazard Identification in Industrial Scenarios | Hanjing Zhou, Mingze Yin, Ying Lian +3 | cs.CV | 2026-09-09 |
| #19 | BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL | Guanqun Zhao, Zijun Xie, Binbin Zheng +3 | cs.LG | 2026-09-09 |
| #20 | Distilling Image Prototypes for Guided Test-Time Adaptation | Liwen Wang, Xingbo Dong, Iman Yi Liao +4 | cs.CV | 2026-09-09 |
| #21 | RouteBridge: Reliability-Routed Bidirectional Distillation Between Neural Radiance Fields and 3D Gaussian Splatting | YuanHang Wang, Xin Cao | cs.CV | 2026-09-09 |
| #22 | Teacher Geometry Shapes Learnability in Teacher-Student Networks | Kai J. Sandbrink, Flavio Martinelli, Alexander van Meegen +2 | cs.LG | 2026-09-09 |
| #23 | Learning with Synthetic Data via SGD in High-Dimensional Linear Regression | Jichu li, Difan Zou | stat.ML | 2026-09-09 |
| #24 | Differentially Private Average Treatment Effect Estimation by Propensity Score Blocking | Duncan Stewardson, Grayson W. White, Adam Groce | stat.ME | 2026-09-08 |
| #25 | Oracle Complexity of Stochastic Fixed-Point Equations with Nonexpansive Maps | Jelena Diakonikolas, Cristóbal Guzmán, David Martínez-Rubio | math.OC | 2026-09-08 |
| #26 | Inductive Biases in Field-Level Cosmological Inference from Galaxy Catalogs | James O. Baldwin, Shy Genel, Francisco Villaescusa-Navarro | astro-ph.CO | 2026-09-08 |
| #27 | Unthrottling the Tanh Jacobian in SAC: A Negative Result on Bang-Bang Control and MetaDrive | Faiq Shamass | cs.LG | 2026-09-08 |
| #28 | Mode Coverage in Normalizing Flow Boltzmann Generators via Log-Ratio Variation | Qi Feng, Rongjie Lai, Di Qi +1 | stat.ML | 2026-09-08 |
| #29 | Do LLMs Make More Mistakes If They Do Not Believe the Input Data? | Peter Kochelka, Aleš Manuel Papáček, Vojtěch Dvořák +1 | cs.CL | 2026-09-08 |
| #30 | Gradland: On Phenomenal Experience, Differentiated Across Many Dimensions | David Balduzzi | cs.AI | 2026-09-08 |
| #31 | Procedural Graphs: Self-Evolving Execution Structures for LLM Agents | Yuxing Lu, Yicheng Chen, Shanchan Wu +1 | cs.AI | 2026-09-08 |
| #32 | Voice or Stereotype? Disentangling Acoustic and Content-Based Gender in Speech-to-Speech Models | Xiaoqun Liu, Tanu Mitra, Harshit Rajgarhia +1 | cs.SD | 2026-09-08 |
| #33 | NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting | Tobias Susetzky, Raphael Rehms, Dmitrii Seletkov +5 | cs.LG | 2026-09-08 |
| #34 | Nearly Tight Rademacher Bounds for Sparsely Activated Neural Networks | Xiaoyu Li, Zhizhou Sha, Jiaojiao Jiang +2 | cs.LG | 2026-09-08 |
| #35 | When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay | Hasan Amin, Wei-Kai Chang, Rajiv Khanna | cs.LG | 2026-09-08 |
| #36 | The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits | Siddharth Vohra, Manikandan Ravikiran | cs.CL | 2026-09-08 |
| #37 | The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation | Aaryaman Kalani, Murari Mandal, Dhruv Kumar +2 | cs.LG | 2026-09-08 |
| #38 | CAST: Canonical Approximate Schur Tree for Approximate Cholesky on Graphs | Meher Chaitanya, Cameron Musco, Aristides Gionis | stat.ML | 2026-09-08 |
| #39 | API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces | Jennifer Wang, Joachim Baumann, Daniel E. Ho +1 | cs.AI | 2026-09-08 |
| #40 | A Closed-Form Estimator and Diagnostic Battery for Anchor-Judge Error Correlation, Under a Single-Common-Factor Model | Veerendra Kumar Sunkavalli | stat.ME | 2026-09-08 |
| #41 | Adaptive Anisotropic Attention for Axis-Structured Signals | Mahir Jain, Parshva Runwal, Aditya Ray Mishra +3 | cs.LG | 2026-09-08 |
| #42 | ZK-Trace: Certified Collusion Tracing with Zero-Knowledge Credentials for Federated GNSS Interference Monitoring | Redwanul Karim, Nisha L. Raichur, Lucas Heublein +3 | cs.CR | 2026-09-08 |
| #43 | A Note on Scaling in Randomly Rotated Quantization and Its Connection to the CDEF +1 Pythagorean Relation | Uri Erez | cs.IT | 2026-09-08 |
| #44 | BAFF: Bid-Aware Filter Family for Mitigating Training Data Interference in RTB A/B Tests | Jeonglyul Oh, Ikkyu Choi, Inseop Youn +1 | cs.LG | 2026-09-08 |
| #45 | Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning | Mohammed-Yassine Habibi, Klea Ziu, Martin Takáč +1 | cs.LG | 2026-09-08 |
| #46 | Navigating the digital spectrum: Assessing political bias, stability, and downstream fairness in Large Language Models | Luka Debevc, Nishan Chatterjee, Antoine Doucet +2 | cs.CL | 2026-09-08 |
| #47 | Do New Attention Mechanisms Actually Fix Attention Sinks at Million-Token Context? | Sara Rizwan, Samaanah Abdus Salam | cs.CL | 2026-09-08 |
| #48 | How to Make the Gradient Mapping Small for Constrained Stochastic Min-Max Problems and Beyond | Ahmet Alacaoglu | math.OC | 2026-09-08 |
| #49 | Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling | Haifeng Wen, Nicolò Michelusi, Osvaldo Simeone +2 | cs.IT | 2026-09-08 |
| #50 | MARS-CLIP: Multi-Resolution and Attention Refined Zero-Shot Image Segmentation | Nagito Saito, Shintaro Ito, Koichi Ito +1 | cs.CV | 2026-09-08 |