| 1 | Elucidating the Design Space of LM Data Attribution | Steven Yu, Sheng-Yu Wang, Kimia Hamidieh +2 | cs.CL | 2026-10-29 |
| 2 | From extreme weather to agricultural consequences with agentic AI | Minghan Yu, Mengyu Dai, Yixin Wen +1 | physics.ao-ph | 2026-10-29 |
| 3 | ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender | Qiyao Ma, Xiaodong Liu, Weiwei Yang +9 | cs.CL | 2026-10-29 |
| #4 | Causal-prior-constrained deep learning for rapid-intensification warning of western North Pacific tropical cyclones | Xinrui Li, Yijun Jin, Yifan Dong +1 | cs.LG | 2026-10-29 |
| #5 | TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents | Guangzhi Wang, Junfu Pu, Yiran Wang +10 | cs.CV | 2026-10-29 |
| #6 | Localizing Concepts in Visual Autoregressive Models | Nanxiang Jiang, Yang Liu, Yuanhao Wang +1 | cs.CV | 2026-10-29 |
| #7 | KV Cache Quantization for Diffusion Language Models | Yan Tai, Yunan Ding, Guangzhao Li +5 | cs.CL | 2026-10-29 |
| #8 | FutureWorld: A Plug-and-Play Causal Next-State Predictor for Interactive Video World Exploration | Guangyuan Li, Kelu Yao, Shuolin Xu +6 | cs.CV | 2026-10-29 |
| #9 | Emergence of the transformer architecture as the score of entropic laws of random measures | Giacomo Greco | cs.AI | 2026-10-29 |
| #10 | 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 |
| #11 | Beyond LLM Wrappers: Context Engineering and the Three-Engine Architecture for Reliable Financial AI | Pradeep Kumar GS, Ravi Tanniru | cs.AI | 2026-10-29 |
| #12 | Reasoning or Pattern Exploitation? Mechanistic Insights from RL-Trained Language Models | Aishik Nagar, Cheston Tan | cs.AI | 2026-10-29 |
| #13 | VEvo-Harness: Causally-Guarded Self-Evolving Harness for Agentic Image Generation | Yuan Wang, Yuhang Yu, Mengting Chen +4 | cs.CV | 2026-10-29 |
| #14 | Kinematic Causal Attribution: Black-Box Explanations of Motion versus Geometry for 4D Point-Cloud Video Models | Zerui Wang | cs.CV | 2026-10-29 |
| #15 | Distilling the Shape of Uncertainty: What On-Policy Distillation Learns and How to Predict It | Shiping Yang, Chuanqi Tang, Hossein Hajimirsadeghi +3 | cs.CL | 2026-10-28 |
| #16 | Interventional Training Reduces Causal Bypass in In-Context Introspection | Zilu Tang, Jongin Kim, Kerem Sahin +3 | cs.CL | 2026-10-28 |
| #17 | Causal Attention on CPU: A Cache-Aware and Load-Balanced Scheduling Kernel for Prefill | Kwun Fung Lau, Frost Mitchell, Kanya Mo +1 | cs.LG | 2026-10-28 |
| #18 | Alpha-TCM: A Nine-Layer Framework for TCM-Guided Multimodal Inference and Structured-Prior Auditing | Yucheng Liu, Everett X. Wang | cs.LG | 2026-10-28 |
| #19 | TCC-RAG: Temporal Causal Chain-Guided RAG for Temporal Knowledge Graph Question Answering | Xinxun Zhang, Yuxiang Wang, Shanshan Feng +6 | cs.CL | 2026-10-28 |
| #20 | Learning a Prior-Data Fitted Network for Graph Foundation Models via Structural Causal Model Priors | Ziwei Zhang, Tianyin Liao, Chunyu Hu +7 | cs.LG | 2026-10-28 |
| #21 | Can LLMs Faithfully Solve Ontology Engineering Tasks? A Mechanistic Interpretability Study | Bohui Zhang, Albert Meroño-Peñuela, Elena Simperl | cs.AI | 2026-10-28 |
| #22 | Vendster: An Evaluation Arena to Investigate How Forecasting Tool Quality Affects LLM Agent Behaviors in Buyer-Vendor Negotiation | Charin Polpanumas | cs.GT | 2026-10-28 |
| #23 | Transportable Offline Reinforcement Learning in Presence of Unmeasured Confounding | Junyi Liao, Hangqi Ren, Zhuoran Yang | cs.LG | 2026-10-28 |
| #24 | Replaying the Same Gradients at a Different $\varepsilon$: A Registered Test of the Fixed-Trajectory Account of Adam's $\varepsilon$ for One Rare Row | Lngel Kyo | cs.LG | 2026-10-28 |
| #25 | The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks | Shuo Wen, Beixi Du, Edwin Meriaux +5 | cs.CV | 2026-10-28 |
| #26 | Evaluating Causal Reasoning in LLMs: A Case Study in the Challenges of Procedural Generation | Justin Clarke, Isha Karn, Patrick Murray +2 | cs.AI | 2026-10-28 |
| #27 | CADENCE: Distributional Next-Transaction Forecasting for Business Cash-Flow Underwriting | Alexander Wu, Jingchao Huang | cs.LG | 2026-10-27 |
| #28 | From Error Prediction to Causal Influence: Auditing SAE Features in Multiple-Choice QA | Aria Nourbakhsh, Adelaide Danilov, Oleksandr Marchenko Breneur +1 | cs.CL | 2026-10-27 |
| #29 | Making Sense of Audience Change: Causal Attribution and Boundary Management on Xiaohongshu | Zhiyi Zhou, Kyrie Zhou | cs.HC | 2026-10-27 |
| #30 | TACOS: Terrain-Aware COntact Supervision for Visual Footstep Planning | Jean-Michel Fortin, William Larrivée-Hardy, Gabriel Jeanson +4 | cs.RO | 2026-10-27 |
| #31 | Timestral | Adrien Petralia, Alexandre Gavaudan, Artjom Joosen +353 | cs.AI | 2026-10-27 |
| #32 | Beyond the Readout: A Latent Numerical Frame Shared Across Modality and Operation | Oriol Juan Sabater, Alex Ferrando de las Morenas, Pau Rodríguez +1 | cs.AI | 2026-10-27 |
| #33 | Mechanistic Failure Modes of Weight Pruning in Transformer Language Models | Nabeelah Faumi, Deshan Sumanathilaka | cs.LG | 2026-10-27 |
| #34 | Correctness Conditioning as Selection in Chain-of-Thought Faithfulness Evaluation | Yueer Pan, Yuexi Pan | cs.AI | 2026-10-27 |
| #35 | Do bots feel bad? Assessing empirical evidence for functional valence in LLMs | Iwan Williams | cs.AI | 2026-10-27 |
| #36 | TDLM: Adaptive Temporal Integration for Diffusion Language Models | Bohang Sun, Max Zhu, Francesco Caso +3 | cs.LG | 2026-10-27 |
| #37 | Making Self-Driving Laboratories Auditable:A Unified Framework for Hybrid Actions,Measurements, and Safe Execution | Zihan Zhang, Zeyu Wu, Xin Zhang +3 | cs.RO | 2026-10-27 |
| #38 | Hy-Nomas: Towards Free-form Interactive World Generation | Qiaoling Chen, Jiaxiang Cheng, Xueqing Deng +35 | cs.CV | 2026-10-27 |
| #39 | From Voiceprints to User Entities: Online Speaker-Memory Construction for Multi-User Spoken Agents | Yucong Zhang, Cancan Li, Bo Xiao +2 | cs.SD | 2026-10-27 |
| #40 | ADTGuard: Adaptive Depth-Time Safeguard for Streaming Inference in Large Language Models | Chuming Wei, Churui Yang, Zihan Zhang +4 | cs.AI | 2026-10-27 |
| #41 | Learning from Points and Patches: A Pre-trained Hybrid Attention Transformer for Time Series Analysis | Peiwang Tang, Cheng HE, Yupeng Ye +3 | cs.LG | 2026-10-27 |
| #42 | Causal Localization of Evidence Effects in Transformers | Jipeng Li, Pramod Khargonekar, Yanning Shen | cs.CL | 2026-10-27 |
| #43 | AC-JEPA: Anchored Cross-Modal Joint Embedding Predictive Architecture for Visual-to-Symbolic Translation | Chaofei Hong, Ziyang Chen, Baochen Wang +2 | cs.AI | 2026-10-27 |
| #44 | FIDES-Live: Evaluating Behavioral Concordance in Sequential Trading Agents | Arther Tian, Alex Ding, Simon Wu +1 | cs.CR | 2026-10-27 |
| #45 | Property-Based Testing for Robust Softmax and Cross-Entropy | Muhammad Maaz | cs.LG | 2026-10-27 |
| #46 | Bridging Exploration and Loss of Plasticity in On-Policy Reinforcement Learning | Andrea Vasco Grieco, Evelyn D'Elia, Edoardo Caldarelli +1 | cs.LG | 2026-10-26 |
| #47 | Cross-modal Steering Vectors Exist Across Both Image and Text Generation | Donghao Zeng, Nishant Subramani, Tamar Rott Shaham +1 | cs.CV | 2026-10-26 |
| #48 | BehaveRec: When Does Long-Term Behavioral History Help Sequential Recommendation? A Study with Session, History, and Community Signals | Aysenur Inan, Reza Yousefi Maragheh, Jayesh Uddhav Kudase +4 | cs.AI | 2026-10-26 |
| #49 | SpatialPC: Deep Computation with Sublinear Local Credit Propagation | Benjamin Prada, Shion Matsumoto, Ankur Arjun Mali | cs.LG | 2026-10-26 |
| #50 | FinLLM-KG: Knowledge Graph-Enhanced LLMs for Financial Sentiment Analysis in Algorithmic Trading | Giorgos Iacovides, Oliver Hannibal, Wuyang Zhou +1 | cs.CL | 2026-10-26 |