arXiv cs.AI Artificial Intelligence

Junting Chen, Yunchuan Li, Panfeng Jiang, Jiacheng Du, Zixuan Chen, Chenrui Tie, Jiajun Deng, Lin Shao: LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating https://arxiv.org/abs/2512.09920 https://arxiv.org/pdf/2512.09920 https://arxiv.org/html/2512.09920

Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov, Yoshua Bengio, Alexander Tong: FALCON: Few-step Accurate Likelihoods for Continuous Flows https://arxiv.org/abs/2512.09914 https://arxiv.org/pdf/2512.09914 https://arxiv.org/html/2512.09914

Erin Craig, Robert Tibshirani: Supervised learning pays attention https://arxiv.org/abs/2512.09912 https://arxiv.org/pdf/2512.09912 https://arxiv.org/html/2512.09912

Salvador Carri\'on, Francisco Casacuberta: Efficient Continual Learning in Neural Machine Translation: A Low-Rank Adaptation Approach https://arxiv.org/abs/2512.09910 https://arxiv.org/pdf/2512.09910 https://arxiv.org/html/2512.09910

Andrew Elashkin, Orna Grumberg: STACHE: Local Black-Box Explanations for Reinforcement Learning Policies https://arxiv.org/abs/2512.09909 https://arxiv.org/pdf/2512.09909 https://arxiv.org/html/2512.09909

Reza Ahmari, Ahmad Mohammadi, Vahid Hemmati, Mohammed Mynuddin, Parham Kebria, Mahmoud Nabil Mahmoud, Xiaohong Yuan, Abdollah Homaifar: Visual Heading Prediction for Autonomous Aerial Vehicles https://arxiv.org/abs/2512.09898 https://arxiv.org/pdf/2512.09898 https://arxiv.org/html/2512.09898

Noah Golowich, Allen Liu, Abhishek Shetty: Provably Learning from Modern Language Models via Low Logit Rank https://arxiv.org/abs/2512.09892 https://arxiv.org/pdf/2512.09892 https://arxiv.org/html/2512.09892

Khurram Khalil, Khaza Anuarul Hoque: FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning https://arxiv.org/abs/2512.09872 https://arxiv.org/pdf/2512.09872 https://arxiv.org/html/2512.09872

Fengli Wu, Vaidehi Patil, Jaehong Yoon, Yue Zhang, Mohit Bansal: MedForget: Hierarchy-Aware Multimodal Unlearning Testbed for Medical AI https://arxiv.org/abs/2512.09867 https://arxiv.org/pdf/2512.09867 https://arxiv.org/html/2512.09867

Simone Corbo: LLMs in Interpreting Legal Documents https://arxiv.org/abs/2512.09830 https://arxiv.org/pdf/2512.09830 https://arxiv.org/html/2512.09830

Xianghao Kong, Zeyu Zhang, Yuwei Guo, Zhuoran Zhao, Songchun Zhang, Anyi Rao: Composing Concepts from Images and Videos via Concept-prompt Binding https://arxiv.org/abs/2512.09824 https://arxiv.org/pdf/2512.09824 https://arxiv.org/html/2512.09824

Jianfei Li, Ines Rosellon-Inclan, Gitta Kutyniok, Jean-Luc Starck: CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing https://arxiv.org/abs/2512.09806 https://arxiv.org/pdf/2512.09806 https://arxiv.org/html/2512.09806

Mohamed Elbayumi, Mohammed S. M. Elbaz: PathCo-LatticE: Pathology-Constrained Lattice-Of Experts Framework for Fully-supervised Few-Shot Cardiac MRI Segmentation https://arxiv.org/abs/2512.09779 https://arxiv.org/pdf/2512.09779 https://arxiv.org/html/2512.09779

Vladimir Balditsyn, Philippe Lalanda, German Vega, St\'ephanie Chollet: Quantifying Uncertainty in Machine Learning-Based Pervasive Systems: Application to Human Activity Recognition https://arxiv.org/abs/2512.09775 https://arxiv.org/pdf/2512.09775 https://arxiv.org/html/2512.09775

Kristof Varadi, Mark Marosi, Peter Antal: Circuits, Features, and Heuristics in Molecular Transformers https://arxiv.org/abs/2512.09757 https://arxiv.org/pdf/2512.09757 https://arxiv.org/html/2512.09757

Jan Betley, Jorio Cocola, Dylan Feng, James Chua, Andy Arditi, Anna Sztyber-Betley, Owain Evans: Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs https://arxiv.org/abs/2512.09742 https://arxiv.org/pdf/2512.09742 https://arxiv.org/html/2512.09742

Laurynas Adomaitis, Vincent Israel-Jost, Alexei Grinbaum: Ethics Readiness of Artificial Intelligence: A Practical Evaluation Method https://arxiv.org/abs/2512.09729 https://arxiv.org/pdf/2512.09729 https://arxiv.org/html/2512.09729

Mika Persson, Jonas Lidman, Jacob Ljungberg, Samuel Sandelius, Adam Andersson: Dynamic one-time delivery of critical data by small and sparse UAV swarms: a model problem for MARL scaling studies https://arxiv.org/abs/2512.09682 https://arxiv.org/pdf/2512.09682 https://arxiv.org/html/2512.09682

Alexey Kravatskiy, Ivan Kozyrev, Nikolai Kozlov, Alexander Vinogradov, Daniil Merkulov, Ivan Oseledets: The Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization https://arxiv.org/abs/2512.09678 https://arxiv.org/pdf/2512.09678 https://arxiv.org/html/2512.09678

Yuzhu Chen, Tian Qin, Xinmei Tian, Fengxiang He, Dacheng Tao: Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power https://arxiv.org/abs/2512.09673 https://arxiv.org/pdf/2512.09673 https://arxiv.org/html/2512.09673

Paloma Piot, David Otero, Patricia Mart\'in-Rodilla, Javier Parapar: Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection https://arxiv.org/abs/2512.09662 https://arxiv.org/pdf/2512.09662 https://arxiv.org/html/2512.09662

Yiwu Zhong, Zi-Yuan Hu, Yin Li, Liwei Wang: Rethinking Chain-of-Thought Reasoning for Videos https://arxiv.org/abs/2512.09616 https://arxiv.org/pdf/2512.09616 https://arxiv.org/html/2512.09616

Boyin Yang, Puming Jiang, Per Ola Kristensson: ImageTalk: Designing a Multimodal AAC Text Generation System Driven by Image Recognition and Natural Language Generation https://arxiv.org/abs/2512.09610 https://arxiv.org/pdf/2512.09610 https://arxiv.org/html/2512.09610

Kjaer, Thapa, Ganjoo, Moore, Jennum, Westover, Zou, Mignot, He, Brink-Kjaer: Stanford Sleep Bench: Evaluating Polysomnography Pre-training Methods for Sleep Foundation Models https://arxiv.org/abs/2512.09591 https://arxiv.org/pdf/2512.09591 https://arxiv.org/html/2512.09591

Prashant Kumar Choudhary, Nouhaila Innan, Muhammad Shafique, Rajeev Singh: Graph-Based Bayesian Optimization for Quantum Circuit Architecture Search with Uncertainty Calibrated Surrogates https://arxiv.org/abs/2512.09586 https://arxiv.org/pdf/2512.09586 https://arxiv.org/html/2512.09586

Dimitrios N. Vlachogiannis, Dimitrios A. Koutsomitropoulos: Hands-on Evaluation of Visual Transformers for Object Recognition and Detection https://arxiv.org/abs/2512.09579 https://arxiv.org/pdf/2512.09579 https://arxiv.org/html/2512.09579

Aris Hofmann, Inge Vejsbjerg, Dhaval Salwala, Elizabeth M. Daly: Auto-BenchmarkCard: Automated Synthesis of Benchmark Documentation https://arxiv.org/abs/2512.09577 https://arxiv.org/pdf/2512.09577 https://arxiv.org/html/2512.09577

Anish Sambamurthy, Ashesh Chattopadhyay: Lazy Diffusion: Mitigating spectral collapse in generative diffusion-based stable autoregressive emulation of turbulent flows https://arxiv.org/abs/2512.09572 https://arxiv.org/pdf/2512.09572 https://arxiv.org/html/2512.09572

Jelena Cupac: The Gender Code: Gendering the Global Governance of Artificial Intelligence https://arxiv.org/abs/2512.09570 https://arxiv.org/pdf/2512.09570 https://arxiv.org/html/2512.09570

Binglin Wu, Jiaxiu Zou, Xianneng Li: System Report for CCL25-Eval Task 10: Prompt-Driven Large Language Model Merge for Fine-Grained Chinese Hate Speech Detection https://arxiv.org/abs/2512.09563 https://arxiv.org/pdf/2512.09563 https://arxiv.org/html/2512.09563