| 1 | A Circuit for In-Context Learning | Andrew Gao, William Gao | cs.CL | 2026-11-03 |
| 2 | Multi-Objective Generative Optimization via Expected Hypervolume Fine-Tuning | Juan Guevara, Riccardo De Santi, Andreas Krause +1 | cs.LG | 2026-11-03 |
| 3 | ScoreDial: Precise Control of Visual Attributes in Image Generation via Regressor Guidance from Limited Human Ratings | Jianbo Tang, Keita Ishii, Hiroki Sakamoto +7 | cs.CV | 2026-11-03 |
| #4 | When Should an LLM Steering Edit Depend on the Input? | Rachael Harkness, Konrad Rawlik | cs.AI | 2026-11-03 |
| #5 | Sample-Grained Approximate Unlearning with Provable Per-Sample Bounds | Yaxin Xiao, Yulin Jin, Li Tang +4 | cs.LG | 2026-11-03 |
| #6 | From Watching to Steering: Enabling Human-Coding Agent Collaboration through Execution Traces | Xiaoke Yan, Jiaying Lei, Danqing Shi +2 | cs.HC | 2026-11-03 |
| #7 | Entropy-Gated Dynamic Rectification for Object Hallucination in Large Vision-Language Models | Riasad Alvi, Md. Asaduzzaman Shuvo, Md. Ahashan Habib +1 | cs.CV | 2026-11-03 |
| #8 | Sparse Internal Control of Language Models | Xizhe Zhang | cs.CL | 2026-11-03 |
| #9 | Drift No More: Spectral Locking for Long-Horizon Open-Weight Multi-Agent AI | Vishal Pramanik, Maisha Maliha, Susmit Jha +1 | cs.AI | 2026-11-03 |
| #10 | Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs | Zihao Feng, Qingzhao Zhang, Chunyu Xia +3 | cs.LG | 2026-11-03 |
| #11 | Co-Occurrence Priors Override Visual Spatial Evidence: Understanding False Alarms in Vision-Language Models for Construction Struck-By Hazard Detection | Xiaoshan Zhou | cs.CV | 2026-11-03 |
| #12 | AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance | Yilun Hao, Ruixiao Yang, Hudson Hilal +5 | cs.AI | 2026-11-02 |
| #13 | Dr. No: Feature Steering for Abstention in Vision-Language Models | Farid Hasanov, Riccardo Renzulli, Bahram Zonooz +2 | cs.LG | 2026-11-02 |
| #14 | Probabilistic Steering of Generative Priors for Lab-in-the-Loop Antibody Optimization | Anisha Parsan, Sebastian Ober, Calvin McCarter +2 | cs.LG | 2026-11-02 |
| #15 | Four Bridges: Measuring Deception Propensity in a Multi-Agent Game | Raphael Casey, Michael Simeone, Alberto Tosato +4 | cs.AI | 2026-11-02 |
| #16 | VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations | Avni Mittal, Avinash Anand, Dikshant Kukreja +3 | cs.CL | 2026-11-02 |
| #17 | Playing Dumb: How a Chess Transformer Simulates Users Across Skill Levels | Difan Jiao, George Eilender, Zhenwei Tang +1 | cs.AI | 2026-11-02 |
| #18 | Steering with Multilingual Lexicons for Sentiment Control in Low-Resource Languages | Lucinda Laurent, Muhammad Dehan Al Kautsar, Alfan Farizki Wicaksono +1 | cs.CL | 2026-11-02 |
| #19 | VERS: Steering Reasoning Models by Editing Their Activation Explanations | Ihor Vitenko | cs.CL | 2026-11-02 |
| #20 | LoRA-Patch: Defending Against Backdoored LoRA Adapters via Directional Steering | Shengyan Huo, Peihai Jiang, Xixiang Lyu +1 | cs.CR | 2026-11-02 |
| #21 | Pair-Relative Partial Equivariance for Rotation-Robust Keypoint Descriptor Matching | Jongmin Lee | cs.CV | 2026-11-02 |
| #22 | What Drives the Zero-to-One Jump? Diagnosing and Steering Hard-Prompt Learning in RLVR | Rui Zhu, Yumou Liu, Zhenzhe Zheng +1 | cs.LG | 2026-11-02 |
| #23 | UPSHIFT: User Preference Steering from Human-AI Interaction Feedback Traces | Jingping Wang, Zhanhao Li, Shao Zhang +1 | cs.AI | 2026-11-02 |
| #24 | SYNC: A Training-Free Inference Controller for Dynamic Layer Selection in Multi-Persona Alignment | Yosef Nuraga Wicaksana, Muhammad Reza Qorib, Fadhil Muhammad +1 | cs.CL | 2026-11-02 |
| #25 | Towards Multi-Value Alignment via Value Localization in LLMs | Xueqi Ma, Yanbei Jiang, Xingjun Ma +2 | cs.AI | 2026-11-02 |
| #26 | Multi-Agent Collusion and the J-Space | Marco Molinari, Gabriele Bettineschi | cs.CL | 2026-11-01 |
| #27 | Beliefs in feedback: Factored representations of interacting agents in transformers | David A. Ehrlich, Manuel Baltieri, Fernando E. Rosas +1 | cs.LG | 2026-11-01 |
| #28 | Spectral Signatures of Memorization Basins in Diffusion Trajectories | Achref Jaziri, Martin Mundt, Ahmed Imtiaz Humayun +1 | cs.LG | 2026-11-01 |
| #29 | Sweep Less, Steer More: Using Activation Steering Geometry for Reduced Hyperparameter Search | Nishkal Hundia, Swastik Agrawal, Navita Goyal +1 | cs.LG | 2026-11-01 |
| #30 | TopoSteer: Topological Layer Selection for Activation Steering in LLMs | Tuc Nguyen, Marcos Gutiérrez-del-Pozo, Eduardo Paluzo-Hidalgo +3 | cs.CL | 2026-11-01 |
| #31 | Information-Theoretic Design of Sparse Autoencoder-Based Steering | Hirofumi Morise | cs.CL | 2026-11-01 |
| #32 | Editing the Goal: Per-Token SAE Steering and Its Depth Limits in $π_{0.5}$ | Rocio Perales Valdes, Animesh Garg | cs.AI | 2026-10-31 |
| #33 | Behavioral Steering of Vision-Language-Action Models in the Low-Parameter Regime | James Tcheng, Feiyu Gavin Zhu | cs.RO | 2026-10-31 |
| #34 | GhostPrefix: Synchronization-Free Universal Prefix Attacks for ASR Manipulation | Shengding Liu, Ashwin Innuganti, Qiben Yan | cs.LG | 2026-10-30 |
| #35 | Task Vectors Can Be Linearly Decomposed into Interpretable and Controllable Components | Yukiya Horiba, Hakaze Cho, Takahiro Yakoh | cs.LG | 2026-10-30 |
| #36 | When Steering Shifts Discourse: Identifying and Intervening on Discourse-Level Changes due to Activation Steering in LLMs | Shivam Adarsh, Hetianyu Huang, Lau Safin +2 | cs.CL | 2026-10-30 |
| #37 | Mechanistic Interpretability for End-to-End Self-Driving | Manav Gagvani, Benjamin Namikas, Sivamurugan Velmurugan +6 | cs.RO | 2026-10-30 |
| #38 | LLM Detoxification via Transition-Aware Reward-Guided Representation Sampling | Aishan Liu, Yisong Xiao, Xianglong Liu +7 | cs.AI | 2026-10-30 |
| #39 | Discovering Interpretable Acoustic Features in Autoregressive Voice-Cloning TTS Models | Anuj Diwan, David Harwath, Eunsol Choi | eess.AS | 2026-10-29 |
| #40 | Composing and Steering Diffusion Models with Generalized Feynman-Kac Correctors | Wael Mattar, Daniel Freedman | cs.LG | 2026-10-29 |
| #41 | Coupled Guidance for Flow Matching | Mateo Clémente, Léo Maxime Brunswic, Rui Heng Yang +1 | cs.LG | 2026-10-29 |
| #42 | One Vector or Many? Clustered Optimal-Transport Steering under Quantization | Illia Makarov | cs.LG | 2026-10-29 |
| #43 | AegisFlow: Training-Free Non-Myopic Path-Safe Guided Flow Matching | Kunpeng Liu, Boshi Zhang, Keyou You | cs.AI | 2026-10-29 |
| #44 | Efficient Covariance-Aware Vicinal Latent Diffusion for Continuous Conditional Image Generation | Xin Ding, Shuo Huang, Zhenglong Ding +5 | cs.CV | 2026-10-29 |
| #45 | AtomSteer: Test-Time Constraint Steering for Atomistic Generative Models | Pengfei Cai, Katharina S. C. Jäger, Utkarsh Utkarsh +4 | cs.LG | 2026-10-28 |
| #46 | Hidden Commitment: When Language Models Silently Pick a Side and How Steering Can Surface It | Samuel Dawit Assefa, Jae Won Cho | cs.CV | 2026-10-28 |
| #47 | Is it my preference? Role Grounding Attack against Agent's Memory via Social Interaction | Haoran Bu, Yiting Shen, Litian Zhang +2 | cs.CR | 2026-10-28 |
| #48 | Human-Residual Steering: Aligning Frozen LLM Judges with Human Judgment Distributions | Chen Lyu, Phong Do, Gabriele Pergola | cs.CL | 2026-10-27 |
| #49 | Spokes, not a Ring: Revisiting the Weekday Manifold in Language Models | Diksha Gupta, Rieke Fruengel, Stefan Heimersheim | cs.LG | 2026-10-27 |
| #50 | Orthogonal and Parametrized Multi-Attribute Steering of LLMs | Remy Ogasawara, Cullen Anderson, Narmeen Fatimah Oozeer +4 | cs.LG | 2026-10-27 |