| 1 | Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection | Keertana Chidambaram, Andrew Ilyas, Vasilis Syrgkanis | cs.AI | 2026-09-14 |
| 2 | A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models | Xingyun Wang, Haomin Zheng, Man Yuan +2 | cs.LG | 2026-09-14 |
| 3 | Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale | Aman Priyanshu, Supriti Vijay, Kimia Majd +8 | cs.CR | 2026-09-14 |
| #4 | Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbation | Zhen Zhong, Shini Yang, Liesheng Wei | cs.LG | 2026-09-14 |
| #5 | LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys | Md Khalid Syfullah, Alvi Ataur Khalil | cs.LG | 2026-09-14 |
| #6 | K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations | Laura M. Vowels, Matthew J. Vowels, Shivali Sharma +9 | cs.CL | 2026-09-14 |
| #7 | Before You Poll with LLMs: A Deliberative Diagnostic Framework | Ahmed Wali, Hassaan Tayyab | cs.CL | 2026-09-14 |
| #8 | Integrating Multi-view Multi-light Surface Reconstruction into Cultural Heritage Workflows | Baptiste Brument, Robin Bruneau, Benjamin Coupry +6 | cs.CV | 2026-09-14 |
| #9 | VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention | Xingyang Li, Dongyun Zou, Shining Zhang +8 | cs.CV | 2026-09-14 |
| #10 | SURE-Map: Self-Correcting Streaming Geometric Foundation Model | Mingkai Liu, Hao Zhao, Xingxing Zuo | cs.CV | 2026-09-14 |
| #11 | MoveBench: A Benchmark for Global-Scale Wildlife Movement Forecasting | Justin Kay, Shir Bar, Ellen O. Aikens +28 | cs.LG | 2026-09-14 |
| #12 | EvoOntology: A Self-Evolving Ontology Layer for Data Agents | Meiduo Chong, Shaolei Zhang, Ju Fan +1 | cs.AI | 2026-09-14 |
| #13 | Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR | Thai Thi Thanh Thao Dang, Mengjie Qian, Kate Knill | cs.CL | 2026-09-14 |
| #14 | Are LLMs Good Financial User Simulators? A Preliminary Study | Jiajie He, Jiangyuan Hong, Dongling Ni +2 | cs.AI | 2026-09-14 |
| #15 | Can a Neural Encoding Model Replicate an fMRI Visualization Study? | Erfan Nasirzadeh Orang, Zack While | cs.HC | 2026-09-14 |
| #16 | MambaMPD: A Mamba-Driven Segmentation Framework for Marine Pollution Detection from Remote Sensing Imagery | Shuaiyu Chen, Wei Han, Peng Ren +2 | cs.CV | 2026-09-14 |
| #17 | CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual Defense | Guo Fuzheng | cs.CR | 2026-09-14 |
| #18 | Where to Compute and How to Interact: Operator-Readable Adaptation with Gauge-Aware Transport | Zixuan Shen, Quanxu Wan, Bingchuan Wang +2 | cs.LG | 2026-09-14 |
| #19 | Bayesian Optimisation Using Product-of-Experts Gaussian Process Models with Uncertainty Calibration | Yean Hoon Ong | cs.LG | 2026-09-14 |
| #20 | To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs | Franck Signe, Hippolyte Pilchen, François Yvon +1 | cs.CL | 2026-09-14 |
| #21 | End-to-End Verifiable and Robust Federated Learning | Doryan Lesaignoux, Enrique Mármol Campos, Gabriele Spini +2 | cs.LG | 2026-09-14 |
| #22 | Authorship attribution and aesthetic evaluation of AI poetry: a case study with Haiku | Livia Oddi, Simone Scardapane, Toru Sugimoto +1 | cs.CL | 2026-09-14 |
| #23 | SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction | Daniel Woortmann, Tanguy Magne, Olga Sorkine-Hornung | cs.CV | 2026-09-14 |
| #24 | Data-driven Prediction of Satellite-observed Avalanche Activity from Snowpack Simulations | Jakob Grahn, Filippo Maria Bianchi, Bert Kruyt +1 | cs.LG | 2026-09-14 |
| #25 | AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation | Shengjie Jin, Zelong Sun, Hengbo Xu +2 | cs.CV | 2026-09-14 |
| #26 | Empirical Evaluation of Task-Based Permission Scoping Architecture for AI Agents | Halil Burak Noyan | cs.AI | 2026-09-14 |
| #27 | MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding | Hongchang Shi, Jinpeng Hu, Ao Wang +4 | cs.CV | 2026-09-14 |
| #28 | Who Teaches Which Token? Verifier-Gated Multi-Expert On-Policy Distillation for Scientific Reasoning | Xun Xu, Zaixi Zhang | cs.AI | 2026-09-14 |
| #29 | Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs | Mark Russinovich, Blake Bullwinkel, Giorgio Severi +2 | cs.CR | 2026-09-14 |
| #30 | Representing Clinical Conditions on Vital Signs from Healthy Individuals using Latent Modeling | Rafael Pina, Varuna De Silva, Mindula Illeperuma | cs.LG | 2026-09-14 |
| #31 | When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis | Kaiyuan Liu, Qiuyang Mang, Bo Peng +6 | cs.CL | 2026-09-14 |
| #32 | Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings | Mingzhou Jiang, Peixi Wu, Hang Cheng +7 | cs.AI | 2026-09-14 |
| #33 | Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures | Yuhang Wang | cs.AI | 2026-09-14 |
| #34 | Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs) | Christian Fisch, Angela Altmeier, Martin Obschonka +2 | cs.CL | 2026-09-14 |
| #35 | A 25-$μ$s/inf Event-driven Graph Neural Network Processor with Spatiotemporal Caching and Spline Convolution for Ultra-low-latency AI at the Edge | Adrian Kneip, Martin Lefebvre, Daniel Gehrig +4 | cs.CV | 2026-09-14 |
| #36 | Unsupervised Point Cloud Registration via Training-Time Semantic Guidance | Kezheng Xiong, Shiyun Xu, Sheng Ao +3 | cs.CV | 2026-09-14 |
| #37 | MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training | Tianyi Xu, Daniel Pimentel-Alarcón, Zuzana Buřivalová +1 | cs.SD | 2026-09-14 |
| #38 | From Ideas to Actions: A Public-Data Decision-Support Toolchain Across the Venture Lifecycle | Lei Qu | cs.AI | 2026-09-14 |
| #39 | Convergence rates for generative drifting flows: fixed-scale obstructions and multihead acceleration | Arthur Stéphanovitch, Eddie Aamari | cs.LG | 2026-09-14 |
| #40 | What Limits Us? Analyzing Self-Reported Limitations in NLP Research | Tawan Thaepprasit, Peeranuth Kehasukcharoen, Ding Wang +3 | cs.CL | 2026-09-14 |
| #41 | EECTracker: Swarm Motion Prior-Guided Feature Compensation for Airborne Optical UAV Swarm Tracking | Zhaochen Chu, Tao Song, Ren Jin +2 | cs.CV | 2026-09-14 |
| #42 | Nearly Minimax-Optimal Regret for Linear Contextual Bandits with Arbitrary Adaptive Action Sets | Tianyuan Jin | cs.LG | 2026-09-14 |
| #43 | PACE: Progressive Angular-to-Norm Contrastive Embedding | Yanping Li, Wei Zhou, Yawen Liu +7 | cs.CV | 2026-09-14 |
| #44 | Improving Mathematical Reasoning Capabilities in Large Language Models via Reasoning Process Error Classification | Runa Yoshida, Kosuke Nishida, Kyosuke Nishida | cs.CL | 2026-09-14 |
| #45 | MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup | Muchen Li, Leonid Sigal, Renjie Liao | cs.CL | 2026-09-14 |
| #46 | $\mathbb{SL}(n)$ Representation Learning: An Intrinsic Mixed-Curvature Space with Higher Curvature Capacities and Deeper Order-Aware Composition | Xingrun Li, Yusuke Mukuta, Xin Yang +2 | cs.LG | 2026-09-14 |
| #47 | Branched Optimal Transport Amortization | Semyon Semenov, Viktor Kovalchuk, Meir Roketlishvili +4 | cs.LG | 2026-09-14 |
| #48 | Rethinking Procedural Audio Pre-training: Source Scaling and Objective Adaptation | Jiajun Peng, Fengrui Liu, Xinyu Liu +1 | cs.SD | 2026-09-14 |
| #49 | Ensemble Complexity in Photovoltaic Forecasting | Sun Ze, Zhou Liguo, Xu Yuqing +2 | cs.LG | 2026-09-14 |
| #50 | Zero-SNR Analyticity of the Scalar MMSE Is Equivalent to Gaussianity | Yixing Zhang | cs.IT | 2026-09-14 |