| 1 | Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration | Jusuk Lee, Sungha Kim, Yeonsoo Park +8 | cs.RO | 2026-10-08 |
| 2 | DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training | Junyan Li, Ruizhi Li, Yu Liu +6 | cs.RO | 2026-10-08 |
| 3 | From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents | Abbas Raftari | cs.CR | 2026-10-08 |
| #4 | What 30,000 Hours of Ego-centric Video Does Not Teach | Jiahua Dong, Anurag Bagchi, Yash Jangir +7 | cs.CV | 2026-10-08 |
| #5 | OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs | You-Zhe Xie, Ting-Wei Chou, Yu-Hsuan Li +3 | cs.CV | 2026-10-08 |
| #6 | OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning | Zhongyu Yang, Jiale Tao, Ruitao Chen +9 | cs.CV | 2026-10-08 |
| #7 | VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation | Boyao Han, Chen Shi, Jingjing Qian +2 | cs.CV | 2026-10-08 |
| #8 | Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception | Oskar J. Hollinsworth, Alex F. Spies, Tigist Diriba +2 | cs.LG | 2026-10-08 |
| #9 | Density Ratio Estimation with Stein Displacement Fields | Song Liu | stat.ML | 2026-10-08 |
| #10 | FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams? | Yuxuan Hu, Weikang Shi, Yang Bo +10 | cs.CV | 2026-10-08 |
| #11 | A Unified Bellman Operator for Safety-Critical Reinforcement Learning | Nishanth Arun Rao, Royina Karegoudra Jayanth, Benjamin Eysenbach +1 | cs.LG | 2026-10-08 |
| #12 | SpaceFlow: Locally Controllable 3D Generation | Neil De La Fuente, Joan Lafuente, Mukhammadali Sayfiddinov +5 | cs.CV | 2026-10-08 |
| #13 | WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation | Jing He, Kaixin Ding, Xingye Tian +5 | cs.CV | 2026-10-08 |
| #14 | Bilevel optimization for data-driven learning of Koopman embeddings using kernel-based autoencoders | Joel-Pascal Ntwali N'konzi, Feliks Nüske, Stefan Klus | cs.LG | 2026-10-08 |
| #15 | Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict | Kaiser Sun, Bernal Jimenez Gutierrez, Hongjun Liu +4 | cs.AI | 2026-10-08 |
| #16 | Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution | Haohui Wang, Jiahao Xu, Wangzhi Zhan +9 | cs.AI | 2026-10-08 |
| #17 | Reasoning-Informed Visual Editing | Xue Yang, Peiyuan Zhang, Yilun Zhu +12 | cs.CV | 2026-10-08 |
| #18 | Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition | Kaisen Yang, Qingle Liu, Kejin Wang +24 | cs.AI | 2026-10-08 |
| #19 | Ambient Discrete Diffusion: Using the Wrong Data at the Right Time for Data Efficient Learning | Julian Kleutgens, Mauricio Tec, Claudio Battiloro +2 | cs.LG | 2026-10-08 |
| #20 | SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference | Qitong Wang, Xinwei Niu, Mingluo Su +3 | cs.LG | 2026-10-08 |
| #21 | Prior or Feedback? What an LLM Uses When Adapting Neural Operators | Julian Chan, Javier Mora Jimenez | cs.AI | 2026-10-08 |
| #22 | A Structural Theory of Cognitive Representation and Problem Solving,Contexts, Invariance, and the Knowledge Space | Antal Jakovác, András Telcs | cs.AI | 2026-10-08 |
| #23 | DVD: Dynamic Vector Decoding for Efficient MLLM-based Perception | Jinghua Hou, Zhe Liu, Hengshuang Zhao | cs.CV | 2026-10-08 |
| #24 | Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings | Youngtaek Oh, Qiyu Wu, Hiromi Wakaki +2 | cs.CV | 2026-10-08 |
| #25 | Batch Before You Lift: Scalable Topological Deep Learning on Large Graphs | David Leko, Luka Benić, Guillermo Bernárdez +3 | cs.LG | 2026-10-08 |
| #26 | RIFT: Relative Isolation From Trees For Anomaly Detection | Mark Daniel Szalai, Gabor Horvath | cs.LG | 2026-10-08 |
| #27 | AdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting | Darahaas Nallagatla, Darryl Cherian Jacob, Pan He | cs.LG | 2026-10-08 |
| #28 | La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching | Runze Ma, Will Hua, Shuangjia Zheng | q-bio.BM | 2026-10-08 |
| #29 | Language Models as AI Research World Models | Zijun Wang, Zewen Liu, Minhua Lin +10 | cs.CL | 2026-10-08 |
| #30 | SciTBERT: A family of chronologically consistent language models for scientific and technological language processing | Thomas Gebhart, Russell J. Funk | cs.CL | 2026-10-08 |
| #31 | DataSense-Bench: The First Step Toward an AI Scientist | Yudi Zhang, Mingyu Cao, Lu Yin +2 | cs.LG | 2026-10-08 |
| #32 | A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization | Ming Chen, Rong-Xi Tan, Ke Xue +8 | cs.LG | 2026-10-08 |
| #33 | AI-Based On-Board Maritime Object Detection for Earth Observation Payload Data Reduction on Versal Embedded Hardware | Thomas Goudemant, Aurélien Bobey, Omar Hlimi +1 | cs.CV | 2026-10-08 |
| #34 | Is Real-World Training Data Necessary for Generalist Graph Anomaly Detection? | Yujing Liu, Yixin Liu, Yue Tan +4 | cs.LG | 2026-10-08 |
| #35 | Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification | Inês Cruchinho Garcia, Mariana Mourão, Francisco Maria Calisto +2 | cs.CV | 2026-10-08 |
| #36 | OA-MAP: Evidence-Grounded Multi-Agent Multimodal Framework for Interpretable Knee Osteoarthritis Progression | Sixu Chen, Mingrui Yang, Qiang Guan +1 | cs.AI | 2026-10-08 |
| #37 | An Investigation of Model Coherence: Narrow Finetunes Contradict Themselves Under Resampling | Robert Graham, Yariv Barsheshat, Phil Blandfort +1 | cs.AI | 2026-10-08 |
| #38 | SuperNav: An Agentic Navigation System for Any Task in Any Scene | Jinkai Zhang, Jingyi Xu, Yuanhong Yu +5 | cs.RO | 2026-10-08 |
| #39 | A persistent accuracy ceiling in automated verbal deception detection | Riccardo Loconte, Jonas Festor, Zane Fatjanova +2 | cs.CL | 2026-10-08 |
| #40 | Universal Textual Teaching for LLMs | Zhanyi Lu, Huan Wang | cs.AI | 2026-10-08 |
| #41 | ContourVLA: A Closed-Loop Perception-Action Contour Policy for Generalized Referring Expression Segmentation | Ruicheng Zhang, Kaiwen Shen, Jiaqi Hou +6 | cs.CV | 2026-10-08 |
| #42 | DVLA-RL++: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning | Wenhao Li, Xianjing Meng, Qiangchang Wang +3 | cs.CV | 2026-10-08 |
| #43 | EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution | Yanning Dai, Yuhui Wang, Nanbo Li +2 | cs.AI | 2026-10-08 |
| #44 | Exploiting Gradients in Bayesian Inference of Expensive Simulators | Šimon Soldát, Václav Šmídl | cs.LG | 2026-10-08 |
| #45 | LIVIN: Benchmarking Spatial and Embodied Intelligence in Digital Twins of Lived-In Homes | Peijun Xu, Chuansen Nie, Yiyang He +13 | cs.CV | 2026-10-08 |
| #46 | MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation | Chenghao Jia, Mengdi Liu, Hong Chang +2 | physics.chem-ph | 2026-10-08 |
| #47 | ILM: An AI-Powered Storytelling Educational Tool | Suhaila Mohammed, Abdelaziz Serour, Allison Lahnala | cs.CL | 2026-10-08 |
| #48 | When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation | Yiruo Cheng, Shen Huang, Xiaoshuai Song +5 | cs.AI | 2026-10-08 |
| #49 | Ghost tasking for parametrized Gaussian Processes solving linear differential equations | Johanna Moser, Christopher Albert, Sascha Ranftl | physics.comp-ph | 2026-10-08 |
| #50 | Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and Limits | Kanghui Ning, Marin Biloš, James T. Wilson +5 | cs.LG | 2026-10-08 |