| 1 | Form and Void: Entangled Composition through an Autonomous AI Agent | Shiwen Wang, Jian Yang, Xu Wang +2 | cs.CV | 2026-10-01 |
| 2 | Task-Adaptive Grounded 3D-Programmers Using 2D VLMs | Arman Raayatsanati, Sombit Dey, Anna-Maria Halacheva +3 | cs.CV | 2026-10-01 |
| 3 | Continual Concept Erasure in Diffusion Models by Suppressing Cross-Edit Interference | Yongliang Wu, Haori Lu, Jinqi Luo +3 | cs.CV | 2026-10-01 |
| #4 | RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models | Yongliang Wu, Haori Lu, Yulun Wu +3 | cs.CV | 2026-10-01 |
| #5 | Anti-Persona: Disrupting Unauthorized Identity Binding and Recognition in Personalized Vision--Language Models | Abhishek Basu, Fahad Shamshad, Karthik Nandakumar | cs.CV | 2026-10-01 |
| #6 | Graph Representation via Elements of Discrete Morse and Cobordism Theories | Jennifer Rozenblit, Chenguang Yang, Yuxin Liu +2 | cs.LG | 2026-10-01 |
| #7 | From Isolated Feature to Orbits: Discovering Music Concepts via Multi-SAE Alignment | Liwei Lin, Gus Xia | cs.SD | 2026-10-01 |
| #8 | Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities | Peng Yi, Ying-Chang Liang | eess.SP | 2026-10-01 |
| #9 | Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models | Tido Specht, Elias Benedict Krey, Nils Neukirch +1 | cs.LG | 2026-10-01 |
| #10 | SkillEvoLean: Mutation-enhanced skill evolution for Lean provers | Kuo Zhou, ZiXion Yang, Lu Zhang | cs.LG | 2026-10-01 |
| #11 | Acmite: Mitigating Gender Bias in LLMs through Concept-Guided Mutual Information | Tian Lan, Xiaoqing Cheng, Han Zhang +1 | cs.CL | 2026-10-01 |
| #12 | Towards a Cloud Fog Edge System for Smart Building | Christophe Cérin, Mamadou Sow, Frédéric Andrès | cs.DC | 2026-10-01 |
| #13 | LLM-Assisted Discovery of Typed Semantic Links for Ontology Network Construction | Nouha Hayouni, Sheeba Samuel, Alsayed Algergawy | cs.CL | 2026-10-01 |
| #14 | CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork | Wojciech Gromski, Patryk Krukowski, Jan Miksa +2 | cs.CV | 2026-10-01 |
| #15 | An ontology for cross-sectoral crisis management: core and public health modules | Aldo Gangemi, Rita T. Sousa, Luigi Asprino +6 | cs.AI | 2026-10-01 |
| #16 | STAGE: Subspace-Targeted Affine Generative Erasure for Text-to-3D Models | Karol Dziekan, Przemysław Spurek, Dawid Malarz | cs.CV | 2026-10-01 |
| #17 | GLoC-EHR: Evidence-Cited Clinical Reasoning over Global Context and Local EHR Events | Chaiho Shin, Kwangsoo Kim | cs.LG | 2026-10-01 |
| #18 | Concept Driven Domain Adaptation: Finding an Abstract Needle in a Haystack | Haiming Zhao, Tai Wang, Kun Zhang +2 | cs.CV | 2026-10-01 |
| #19 | A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform | Chengkai Xu, Yiming Cui, Jiaqi Liu +7 | cs.RO | 2026-10-01 |
| #20 | An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design | Sara Riazi, Pedram Rooshenas | cs.AI | 2026-10-01 |
| #21 | On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D | Fabio J. Fehr, Philip Torr | cs.LG | 2026-09-30 |
| #22 | Video Generation Models: A Survey of Post-Training and Alignment | Chaoyu Li, Xiaoyi Gu, Yogesh Kulkarni +10 | cs.CV | 2026-09-30 |
| #23 | Can large language models unlock discrete data in ophthalmic diagnostic reports? | Umair A. Zaidi, An-Lun Wu, Wei-Chun Lin +2 | cs.CL | 2026-09-30 |
| #24 | Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving | Huiwen Yan, Kyriakos G. Vamvoudakis, Mushuang Liu | cs.AI | 2026-09-30 |
| #25 | Lingtai: What Concept Geometry Reveals--and Does Not Reveal--About LLM Inference | Jiangang Chen | cs.CL | 2026-09-30 |
| #26 | Group-Invariant Statistics Determine Embedding Geometry: Harmonic Analysis of Representations from Bach to the Night Sky | Liam Storan, Andreas Tolias, Nina Miolane | cs.LG | 2026-09-30 |
| #27 | Beyond Affine Transformations: A Soft Dominance Layer for Coordinate-Wise Neural Computation | Mariano Rivera | cs.LG | 2026-09-30 |
| #28 | Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning | Sachi Shome, William Eiers | cs.LG | 2026-09-30 |
| #29 | AutoDataBench: A Data-centric Testbed for Accelerating Auto Research | Ruifeng Yuan, Yizhi Li, Yaxin Du +9 | cs.CL | 2026-09-30 |
| #30 | DoGBench: Can Agents Meet Expert Standards for User-Facing Documentation? | Frances Liu, Manny Silva, Paige Calvert +2 | cs.SE | 2026-09-30 |
| #31 | Understanding Parents' Complex Views of AI for Children's Pretend Play | Sungho Oh, Mohammad Namvarpour, Maxi Heitmayer +2 | cs.HC | 2026-09-30 |
| #32 | Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations | Maximilian von Klinski, Sebastian Lapuschkin, Wojciech Samek +1 | cs.CL | 2026-09-30 |
| #33 | Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision | Weijian Jian, Xiaoyue Zhang, Bin Xiao +5 | cs.CV | 2026-09-30 |
| #34 | ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models | Tobia Poppi, Silvia Cappelletti, Samuele Poppi +4 | cs.CV | 2026-09-30 |
| #35 | MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentation | Ivan Martinović, Josip Šarić, Yuki M. Asano +1 | cs.CV | 2026-09-30 |
| #36 | D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders | Xinyue Xu, Jiahao Zhang, Lijie Hu +2 | cs.CV | 2026-09-30 |
| #37 | FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning | Łukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk +1 | cs.CV | 2026-09-30 |
| #38 | Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond | Simone Facchiano, Jan Eric Lenssen, Bernt Schiele +3 | cs.CV | 2026-09-30 |
| #39 | Candidate Retention for Abductive Learning | Hao-Yuan He, Yu Liu, Ming Li | cs.LG | 2026-09-30 |
| #40 | Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song Generation | Arhan Vohra, Choenden Kyirong, Laura Ibáñez-Martínez +1 | cs.SD | 2026-09-30 |
| #41 | CIDER-FM: Foundation Models for Causal Inference from Diverse Experimental Regimes | Yuche Gao, Arik Reuter, Siyuan Guo +3 | cs.LG | 2026-09-30 |
| #42 | Can Domain Generalization be Guaranteed in Small-Sample Learning? | Hong Zheng | cs.LG | 2026-09-30 |
| #43 | Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning | Quan M. Tran, Zhuo Huang, Zhen Fang +3 | cs.AI | 2026-09-30 |
| #44 | From Speech to Editable Concepts: Probing Emotion Recognition with Concept Bottleneck Models | Hezhao Zhang, Thomas Hain | cs.SD | 2026-09-30 |
| #45 | Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents | Wenxin Wu, Lingyong Yan, Lei Sha +2 | cs.CR | 2026-09-30 |
| #46 | PLRS-IC: A Dual-Calibration Framework for Chest X-Ray Vision-Language Alignment | Qixing Zhao, Jinpeng Li | cs.CV | 2026-09-30 |
| #47 | Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation | Ziqi Zhou, Yifan Hu, Yufei Song +5 | cs.CV | 2026-09-30 |
| #48 | Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of Readout | Aojie Yuan, Zhiyuan Julian Su, Haiyue Zhang +1 | cs.CL | 2026-09-30 |
| #49 | Trust the Critic More | Kaiyue Wen, Luke Bailey, Arvind Mahankali +1 | cs.LG | 2026-09-30 |
| #50 | A strategic roadmap for an atomistic machine-learning ecosystem | Jörg Behler, Michele Ceriotti, Cecilia Clementi +46 | physics.chem-ph | 2026-09-30 |