arXiv cs.AI Artificial Intelligence

Li, Shang, Liu, Zhan, Wang, Wang, Chen, Wang, An, Tang, Hou, Fan, Zhang: DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving https://arxiv.org/abs/2510.12796 https://arxiv.org/pdf/2510.12796 https://arxiv.org/html/2510.12796

Caner Korkmaz, Brighton Nuwagira, Bar{\i}\c{s} Co\c{s}kunuzer, Tolga Birdal: CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations https://arxiv.org/abs/2510.12795 https://arxiv.org/pdf/2510.12795 https://arxiv.org/html/2510.12795

Kevin Li, Manuel Brack, Sudeep Katakol, Hareesh Ravi, Ajinkya Kale: UniFusion: Vision-Language Model as Unified Encoder in Image Generation https://arxiv.org/abs/2510.12789 https://arxiv.org/pdf/2510.12789 https://arxiv.org/html/2510.12789

Felix Taubner, Ruihang Zhang, Mathieu Tuli, Sherwin Bahmani, David B. Lindell: MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars https://arxiv.org/abs/2510.12785 https://arxiv.org/pdf/2510.12785 https://arxiv.org/html/2510.12785

Ahmed Heakl, Martin Gubri, Salman Khan, Sangdoo Yun, Seong Joon Oh: Dr.LLM: Dynamic Layer Routing in LLMs https://arxiv.org/abs/2510.12773 https://arxiv.org/pdf/2510.12773 https://arxiv.org/html/2510.12773

Fengzhi Guo, Chih-Chuan Hsu, Sihao Ding, Cheng Zhang: Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction https://arxiv.org/abs/2510.12768 https://arxiv.org/pdf/2510.12768 https://arxiv.org/html/2510.12768

Saurabh Sihag, Gonzalo Mateos, Alejandro Ribeiro: Disentangling Neurodegeneration with Brain Age Gap Prediction Models: A Graph Signal Processing Perspective https://arxiv.org/abs/2510.12763 https://arxiv.org/pdf/2510.12763 https://arxiv.org/html/2510.12763

A. Alfarano, L. Venturoli, D. Negueruela del Castillo: VQArt-Bench: A semantically rich VQA Benchmark for Art and Cultural Heritage https://arxiv.org/abs/2510.12750 https://arxiv.org/pdf/2510.12750 https://arxiv.org/html/2510.12750

Sanghee J. Kim, Kanishka Misra: Hey, wait a minute: on at-issue sensitivity in Language Models https://arxiv.org/abs/2510.12740 https://arxiv.org/pdf/2510.12740 https://arxiv.org/html/2510.12740

Hang Yu, Julian Jordan, Julian Schmidt, Silvan Lindner, Alessandro Canevaro, Wilhelm Stork: HYPE: Hybrid Planning with Ego Proposal-Conditioned Predictions https://arxiv.org/abs/2510.12733 https://arxiv.org/pdf/2510.12733 https://arxiv.org/html/2510.12733

Anas Abouaomar, Mohammed El hanjri, Abdellatif Kobbane, Anis Laouiti, Khalid Nafil: Hierarchical Federated Learning for Crop Yield Prediction in Smart Agricultural Production Systems https://arxiv.org/abs/2510.12727 https://arxiv.org/pdf/2510.12727 https://arxiv.org/html/2510.12727

Montes, et al.: Artificial intelligence for simplified patient-centered dosimetry in radiopharmaceutical therapies https://arxiv.org/abs/2510.12714 https://arxiv.org/pdf/2510.12714 https://arxiv.org/html/2510.12714

Guo, Tyagi, Gosai, Vergara, Montoya, Zhang, Hu, He, Liu, Srinivasa: Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning https://arxiv.org/abs/2510.12712 https://arxiv.org/pdf/2510.12712 https://arxiv.org/html/2510.12712

Shelley Zixin Shu, Haozhe Luo, Alexander Poellinger, Mauricio Reyes: Hybrid Explanation-Guided Learning for Transformer-Based Chest X-Ray Diagnosis https://arxiv.org/abs/2510.12704 https://arxiv.org/pdf/2510.12704 https://arxiv.org/html/2510.12704

Cedric Richter, Heike Wehrheim: Beyond Postconditions: Can Large Language Models infer Formal Contracts for Automatic Software Verification? https://arxiv.org/abs/2510.12702 https://arxiv.org/pdf/2510.12702 https://arxiv.org/html/2510.12702

Vicente Bosca, Tatum Rask, Sunia Tanweer, Andrew R. Tawfeek, Branden Stone: Topological Signatures of ReLU Neural Network Activation Patterns https://arxiv.org/abs/2510.12700 https://arxiv.org/pdf/2510.12700 https://arxiv.org/html/2510.12700

Sunny Yu, Ahmad Jabbar, Robert Hawkins, Dan Jurafsky, Myra Cheng: Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations https://arxiv.org/abs/2510.12699 https://arxiv.org/pdf/2510.12699 https://arxiv.org/html/2510.12699

Sarina Xi, Orelia Pi, Miaomiao Zhang, Becca Xiong, Jacqueline Ng Lane, Nihar B. Shah: Who is a Better Matchmaker? Human vs. Algorithmic Judge Assignment in a High-Stakes Startup Competition https://arxiv.org/abs/2510.12692 https://arxiv.org/pdf/2510.12692 https://arxiv.org/html/2510.12692

Danial Hosseintabar, Fan Chen, Giannis Daras, Antonio Torralba, Constantinos Daskalakis: DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization https://arxiv.org/abs/2510.12691 https://arxiv.org/pdf/2510.12691 https://arxiv.org/html/2510.12691

Suyash Fulay, Jocelyn Zhu, Michiel Bakker: From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM https://arxiv.org/abs/2510.12689 https://arxiv.org/pdf/2510.12689 https://arxiv.org/html/2510.12689

Shouren Wang, Wang Yang, Xianxuan Long, Qifan Wang, Vipin Chaudhary, Xiaotian Han: Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think? https://arxiv.org/abs/2510.12680 https://arxiv.org/pdf/2510.12680 https://arxiv.org/html/2510.12680

Chih-Chuan Cheng, Yi-Ju Tseng: SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning https://arxiv.org/abs/2510.12659 https://arxiv.org/pdf/2510.12659 https://arxiv.org/html/2510.12659

Chaoxu Pang, Yixuan Cao, Ping Luo: Reasoning Pattern Matters: Learning to Reason without Human Rationales https://arxiv.org/abs/2510.12643 https://arxiv.org/pdf/2510.12643 https://arxiv.org/html/2510.12643

Meihui Zhang, Liming Wang, Chi Zhang, Zhaojing Luo: Aixel: A Unified, Adaptive and Extensible System for AI-powered Data Analysis https://arxiv.org/abs/2510.12642 https://arxiv.org/pdf/2510.12642 https://arxiv.org/html/2510.12642

Sheng, Tong, Wan, Zhang, Jia, Wu, Wu, Li, Zhang, Peng, Lin, Liu, Wu: Laminar: A Scalable Asynchronous RL Post-Training Framework https://arxiv.org/abs/2510.12633 https://arxiv.org/pdf/2510.12633 https://arxiv.org/html/2510.12633

Ajith Anil Meera, Abian Torres, Pablo Lanillos: Designing Tools with Control Confidence https://arxiv.org/abs/2510.12630 https://arxiv.org/pdf/2510.12630 https://arxiv.org/html/2510.12630

Yuta Kobayashi, Zilin Jing, Jiayu Yao, Hongseok Namkoong, Shalmali Joshi: Learning-To-Measure: In-context Active Feature Acquisition https://arxiv.org/abs/2510.12624 https://arxiv.org/pdf/2510.12624 https://arxiv.org/html/2510.12624

Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis: Rethinking Knowledge Distillation: A Data Dependent Regulariser With a Negative Asymmetric Payoff https://arxiv.org/abs/2510.12615 https://arxiv.org/pdf/2510.12615 https://arxiv.org/html/2510.12615

Siyuan Li, Aodu Wulianghai, Xi Lin, Guangyan Li, Xiang Chen, Jun Wu, Jianhua Li: StyleDecipher: Robust and Explainable Detection of LLM-Generated Texts with Stylistic Analysis https://arxiv.org/abs/2510.12608 https://arxiv.org/pdf/2510.12608 https://arxiv.org/html/2510.12608

Zhao, Sun, Zheng, Guo, Wang, Liang, Peng, Chen, Lei: SMILE: SeMantic Ids Enhanced CoLd Item Representation for Click-through Rate Prediction in E-commerce SEarch https://arxiv.org/abs/2510.12604 https://arxiv.org/pdf/2510.12604 https://arxiv.org/html/2510.12604