arXiv cs.AI Artificial Intelligence

Iv\'an Arcuschin, David Chanin, Adri\`a Garriga-Alonso, Oana-Maria Camburu: Biases in the Blind Spot: Detecting What LLMs Fail to Mention https://arxiv.org/abs/2602.10117 https://arxiv.org/pdf/2602.10117 https://arxiv.org/html/2602.10117

Yuxin Jiang, Yuchao Gu, Ivor W. Tsang, Mike Zheng Shou: Olaf-World: Orienting Latent Actions for Video World Modeling https://arxiv.org/abs/2602.10104 https://arxiv.org/pdf/2602.10104 https://arxiv.org/html/2602.10104

Georgios Kaissis, David Mildenberger, Juan Felipe Gomez, Martin J. Menten, Eleni Triantafillou: Step-resolved data attribution for looped transformers https://arxiv.org/abs/2602.10097 https://arxiv.org/pdf/2602.10097 https://arxiv.org/html/2602.10097

Xingjian Bai, Guande He, Zhengqi Li, Eli Shechtman, Xun Huang, Zongze Wu: Causality in Video Diffusers is Separable from Denoising https://arxiv.org/abs/2602.10095 https://arxiv.org/pdf/2602.10095 https://arxiv.org/html/2602.10095

Xuehang Guo, Zhiyong Lu, Tom Hope, Qingyun Wang: Anagent For Enhancing Scientific Table & Figure Analysis https://arxiv.org/abs/2602.10081 https://arxiv.org/pdf/2602.10081 https://arxiv.org/html/2602.10081

Xinchen Han, Hossam Afifi, Michel Marot, Xilu Wang, Lu Yin: Long Chain-of-Thought Compression via Fine-Grained Group Policy Optimization https://arxiv.org/abs/2602.10048 https://arxiv.org/pdf/2602.10048 https://arxiv.org/html/2602.10048

Akshay Mete, Shahid Aamir Sheikh, Tzu-Hsiang Lin, Dileep Kalathil, P. R. Kumar: Optimistic World Models: Efficient Exploration in Model-Based Deep Reinforcement Learning https://arxiv.org/abs/2602.10044 https://arxiv.org/pdf/2602.10044 https://arxiv.org/html/2602.10044

Changjiang Jiang, Xinkuan Sha, Fengchang Yu, Jingjing Liu, Jian Liu, Mingqi Fang, Chenfeng Zhang, Wei Lu: Fake-HR1: Rethinking reasoning of vision language model for synthetic image detection https://arxiv.org/abs/2602.10042 https://arxiv.org/pdf/2602.10042 https://arxiv.org/html/2602.10042

Wenxuan Xie, Yujia Wang, Xin Tan, Chaochao Lu, Xia Hu, Xuhong Wang: Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference https://arxiv.org/abs/2602.10021 https://arxiv.org/pdf/2602.10021 https://arxiv.org/html/2602.10021

Qingnan Ren, Shiting Huang, Zhen Fang, Zehui Chen, Lin Chen, Lijun Li, Feng Zhao: ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning https://arxiv.org/abs/2602.10019 https://arxiv.org/pdf/2602.10019 https://arxiv.org/html/2602.10019

Bojian Hou, et al.: Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design https://arxiv.org/abs/2602.10016 https://arxiv.org/pdf/2602.10016 https://arxiv.org/html/2602.10016

Sharma, Sharma, Reberio, Kesharwani, Thakur, Dhar, Behera: RoboSubtaskNet: Temporal Sub-task Segmentation for Human-to-Robot Skill Transfer in Real-World Environments https://arxiv.org/abs/2602.10015 https://arxiv.org/pdf/2602.10015 https://arxiv.org/html/2602.10015

Bharathkumar Hegde, Melanie Bouroche: A Collaborative Safety Shield for Safe and Efficient CAV Lane Changes in Congested On-Ramp Merging https://arxiv.org/abs/2602.10007 https://arxiv.org/pdf/2602.10007 https://arxiv.org/html/2602.10007

Xiulin Yang, Arianna Bisazza, Nathan Schneider, Ethan Gotlieb Wilcox: A Unified Assessment of the Poverty of the Stimulus Argument for Neural Language Models https://arxiv.org/abs/2602.09992 https://arxiv.org/pdf/2602.09992 https://arxiv.org/html/2602.09992

Enzo Nicolas Spotorno, Josafat Leal Filho, Antonio Augusto Medeiros Frohlich: Empirical Stability Analysis of Kolmogorov-Arnold Networks in Hard-Constrained Recurrent Physics-Informed Discovery https://arxiv.org/abs/2602.09988 https://arxiv.org/pdf/2602.09988 https://arxiv.org/html/2602.09988

J Rosser, Robert Kirk, Edward Grefenstette, Jakob Foerster, Laura Ruis: Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions https://arxiv.org/abs/2602.09987 https://arxiv.org/pdf/2602.09987 https://arxiv.org/html/2602.09987

Alexander Fertig, Karthikeyan Chandra Sekaran, Lakshman Balasubramanian, Michael Botsch: Online Monitoring Framework for Automotive Time Series Data using JEPA Embeddings https://arxiv.org/abs/2602.09985 https://arxiv.org/pdf/2602.09985 https://arxiv.org/html/2602.09985

Calvin Yeung, Ali Zakeri, Zhuowen Zou, Mohsen Imani: Coupled Inference in Diffusion Models for Semantic Decomposition https://arxiv.org/abs/2602.09983 https://arxiv.org/pdf/2602.09983 https://arxiv.org/html/2602.09983

Enzo Nicolas Spotorno, Josafat Ribeiro Leal, Antonio Augusto Frohlich: Supervised Metric Regularization Through Alternating Optimization for Multi-Regime Physics-Informed Neural Networks https://arxiv.org/abs/2602.09980 https://arxiv.org/pdf/2602.09980 https://arxiv.org/html/2602.09980

Daanish Aleem Qureshi, Khemraj Shukla, Vikas Srivastava: Drug Release Modeling using Physics-Informed Neural Networks https://arxiv.org/abs/2602.09963 https://arxiv.org/pdf/2602.09963 https://arxiv.org/html/2602.09963

Franziska Krau{\ss}, Matthias Ege, Zoltan Lovasz, Albrecht Bartz-Schmidt, Igor Tsaur, Oliver Sawodny, Carina Veil: Bladder Vessel Segmentation using a Hybrid Attention-Convolution Framework https://arxiv.org/abs/2602.09949 https://arxiv.org/pdf/2602.09949 https://arxiv.org/html/2602.09949

Sharma, Sharma, Rebeiro, Thakur, Dhar, Behera: Instruct2Act: From Human Instruction to Actions Sequencing and Execution via Robot Action Network for Robotic Manipulation https://arxiv.org/abs/2602.09940 https://arxiv.org/pdf/2602.09940 https://arxiv.org/html/2602.09940

Qahqaie, Neumann, Heimann, Maier, Zimmer: Unbalanced optimal transport for robust longitudinal lesion evolution with registration-aware and appearance-guided priors https://arxiv.org/abs/2602.09933 https://arxiv.org/pdf/2602.09933 https://arxiv.org/html/2602.09933

Zongrui Li, Xinhua Ma, Minghui Hu, Yunqing Zhao, Yingchen Yu, Qian Zheng, Chang Liu, Xudong Jiang, Song Bai: Monocular Normal Estimation via Shading Sequence Estimation https://arxiv.org/abs/2602.09929 https://arxiv.org/pdf/2602.09929 https://arxiv.org/html/2602.09929

William Lugoloobi, Thomas Foster, William Bankes, Chris Russell: LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations https://arxiv.org/abs/2602.09924 https://arxiv.org/pdf/2602.09924 https://arxiv.org/html/2602.09924

Gulraiz Khan, Kenneth Y. Wertheim, Kevin Pimbblet, Waqas Ahmed: SARS: A Novel Face and Body Shape and Appearance Aware 3D Reconstruction System extends Morphable Models https://arxiv.org/abs/2602.09918 https://arxiv.org/pdf/2602.09918 https://arxiv.org/html/2602.09918

Yue Fu, Joel Wester, Niels Van Berkel, Alexis Hiniker: Self-Regulated Reading with AI Support: An Eight-Week Study with Students https://arxiv.org/abs/2602.09907 https://arxiv.org/pdf/2602.09907 https://arxiv.org/html/2602.09907

Rafid Mahmood: Routing, Cascades, and User Choice for LLMs https://arxiv.org/abs/2602.09902 https://arxiv.org/pdf/2602.09902 https://arxiv.org/html/2602.09902

Zhengxue Cheng, Yan Zhao, Keyu Wang, Hengdi Zhang, Li Song: TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile Data https://arxiv.org/abs/2602.09893 https://arxiv.org/pdf/2602.09893 https://arxiv.org/html/2602.09893

Yuhao Zheng, Li'an Zhong, Yi Wang, Rui Dai, Kaikui Liu, Xiangxiang Chu, Linyuan Lv, Philip Torr, Kevin Qinghong Lin: Code2World: A GUI World Model via Renderable Code Generation https://arxiv.org/abs/2602.09856 https://arxiv.org/pdf/2602.09856 https://arxiv.org/html/2602.09856