| 1 | Elucidating the Design Space of LM Data Attribution | Steven Yu, Sheng-Yu Wang, Kimia Hamidieh +2 | cs.CL | 2026-10-29 |
| 2 | Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers | Jiongfan Yang, Weichen Fan, Haiwen Diao +2 | cs.CV | 2026-10-29 |
| 3 | ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender | Qiyao Ma, Xiaodong Liu, Weiwei Yang +9 | cs.CL | 2026-10-29 |
| #4 | An ODE-based Sampler for Discrete Diffusion Models | Samson Gourevitch, Yazid Janati, Eric Moulines +3 | cs.LG | 2026-10-29 |
| #5 | TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races | Tom Sander, Pierre Fernandez, Itai Gat +11 | cs.CR | 2026-10-29 |
| #6 | HairDeck: Animation-Ready Stylized Hair Cards from a Single Image | Yuze He, Yixiang Wei, Wang Zhao +3 | cs.CV | 2026-10-29 |
| #7 | Pre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In | Leonidas Raghav | cs.AI | 2026-10-29 |
| #8 | RADIOlogy: A Single-Pass Approach to Training-Free Zero-Shot Anomaly Detection | Joaquín Figueira, Giacomo D'Amicantonio, Egor Bondarau | cs.CV | 2026-10-29 |
| #9 | Multi-View MoE: Letting Every Router Shape Expert Computation | Zelin Zhao, Tianchi Ma, Junyuan Shang +2 | cs.CL | 2026-10-29 |
| #10 | PIVOT: Progressive Intervention via Online Teacher Correction | Zhihao Yang, Boyuan Zheng, Puhui Tan +7 | cs.CL | 2026-10-29 |
| #11 | Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation | Yifu Luo, Chuang Ma, Zeyu Chen +3 | cs.CL | 2026-10-29 |
| #12 | Retrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents | Daniel Strauß, Zhenshan Bing, Alois Knoll | cs.AI | 2026-10-29 |
| #13 | On the Fundamental Limits of Prefill-Based Decoding Length Prediction | Haowen Shi, Xuzhe Yan, Fahao Chen +1 | cs.AI | 2026-10-29 |
| #14 | Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese | Pedro Carvalho Brom | cs.CL | 2026-10-29 |
| #15 | IndicIPR-QA: A Benchmark for Extractive Question Answering on Indian IPR Laws | M. Mohaiminul Islam, Muhammad Abulaish | cs.CL | 2026-10-29 |
| #16 | Glance: The Generator Is Its Own Reranker | Adilet Metinov, Chingiz Arziev | cs.CL | 2026-10-29 |
| #17 | Understanding and Mitigating Role Spoofing in LLMs | Ezra Edelman, Benjamin Edelman, Surbhi Goel +1 | cs.CR | 2026-10-29 |
| #18 | Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training | Qifan Yu, Xinyu Ma, Xingyan Bin +1 | cs.LG | 2026-10-29 |
| #19 | Don't Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation | Zheng Zhu, Xiaozhuan Liang, Xi Chen +2 | cs.CL | 2026-10-29 |
| #20 | RFW-A: Agentic Procedural Generation of 400K Articulated Assets over 500 Categories | Yuanbo Lyu, Changjian Pan, Saining Zhang +19 | cs.CV | 2026-10-29 |
| #21 | How to Loop Your Transformer: Loop Scaling, Specialization, and Parallel Inference | Chanakya Ekbote, Artidoro Pagnoni, Devendra Singh Sachan +5 | cs.LG | 2026-10-29 |
| #22 | Only Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets | Bole Ma, Ayesha Afzal, Jan Eitzinger +2 | cs.DC | 2026-10-29 |
| #23 | Neighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering | Mesut Ceylan, Arda Baris Basaran, Elgar Fleisch +1 | cs.AI | 2026-10-29 |
| #24 | TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents | Guangzhi Wang, Junfu Pu, Yiran Wang +10 | cs.CV | 2026-10-29 |
| #25 | Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR | Lang Chen, Zongxin Xu, Borui Wang +2 | cs.AI | 2026-10-29 |
| #26 | Understanding axial attention in TSFMs through single location regression | Andrei-Tiberiu Pantea, Aymeric Dieuleveut | stat.ML | 2026-10-29 |
| #27 | Mode Dynamics: A Framework for Neural Network Learning | Hossein Honarvar | cs.LG | 2026-10-29 |
| #28 | One Vector or Many? Clustered Optimal-Transport Steering under Quantization | Illia Makarov | cs.LG | 2026-10-29 |
| #29 | Rethinking Pre-pretraining | Alexander Stern, Tim Rocktäschel, Acyr Locatelli +1 | cs.CL | 2026-10-29 |
| #30 | UniRA: Unified Representation Alignment and Auto-Encoding for Efficient Diffusion Generation | An Lanji, Dawei Liu, Jin Li +3 | cs.CV | 2026-10-29 |
| #31 | Prompts and probabilities in the linguistic assessment of language models: Evidence from semantic focus-sensitivity | Robert Pasternak | cs.CL | 2026-10-29 |
| #32 | Tokenizer Tokens Tell Training Tales | Nishita Jain, Parth Upman, Shreyank N Gowda | cs.CL | 2026-10-29 |
| #33 | TokenRepel: Generating Diverse Image Sets Without Compromising Quality | Qingtao Yu, Zhen Wang, Ning Lai +3 | cs.CV | 2026-10-29 |
| #34 | Attention, Dynamic Wave and Hybrid Sequence Mixers in Language Models | Dmytro Babarytskyi, Oleksandr Babarytskyi | cs.LG | 2026-10-29 |
| #35 | KV Cache Quantization for Diffusion Language Models | Yan Tai, Yunan Ding, Guangzhao Li +5 | cs.CL | 2026-10-29 |
| #36 | DWISE: Denoising Workload-Informed Scheduling Engine | Lie Li, Wen Li, Junxiao Shen +2 | cs.LG | 2026-10-29 |
| #37 | InferD: A Honeypot Framework for AI Inference Infrastructure | Hicham Hammouchi, Gabriele Lenzini | cs.CR | 2026-10-29 |
| #38 | AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers | Bin Xu, Mo Zhang, Zhengfeiyang Zhang +6 | cs.CV | 2026-10-29 |
| #39 | Look at Where You Think: Localization-Head Alignment for Fine-Grained Perception in Thinking VLMs | Yuan Wang, Wei Wu, Hongning Wang | cs.CV | 2026-10-29 |
| #40 | The Real Cost of Context: Predicting Compute Time and Energy Consumption in LLM Prefill and Decode Phases | Lars Krupp, Daniel Geißler, Francisco M. Calatrava-Nicolas +3 | cs.AI | 2026-10-29 |
| #41 | Emergence of the transformer architecture as the score of entropic laws of random measures | Giacomo Greco | cs.AI | 2026-10-29 |
| #42 | DiFuse: Fusing Native Diffusion Representations for Spatial Reasoning in Unified Multimodal Models | Ruixin Fan, Weining Wang, Jiahui Sun +2 | cs.CV | 2026-10-29 |
| #43 | Raincheck: Deferred Multimodal Prefill for Efficient Multi-Turn MLLM Inference | Wenjie Huang, Jun Zhang, Hongyaoxing Gu +10 | cs.CL | 2026-10-29 |
| #44 | LatentWeave: Test-Time Latent Optimization for Multimodal Reasoning | Fanci Meng, Kun Wang, Guibin Zhang +4 | cs.LG | 2026-10-29 |
| #45 | ROAD: Modern Adversarial Training for Simple One-Step Distillation at Scale | Xiaoou Li, Shan You, Tao Huang | cs.CV | 2026-10-29 |
| #46 | MOSAIC-Flow: Orthogonal-Axis and Status-Conditioned Fusion for Missing-Sequence Completion in Brain Tumor MRI | Pengli Zhu, Zhihao Peng, Yixuan Yuan | cs.CV | 2026-10-29 |
| #47 | Regional Anchor Routing for Multi-Object Motion Transfer | Yuze Li, Fuchen Long, Xinlong Sun +3 | cs.CV | 2026-10-29 |
| #48 | Calibrating Attention-Based Token Pruning for Efficient Multi-Image Synthesis in UMMs | Zimeng Wu, Qijian Tian, Penghui Du +3 | cs.CV | 2026-10-29 |
| #49 | End-to-End Guarantees for Masked Diffusion Models under Conditional Mixing | Fareed Sheriff | cs.LG | 2026-10-29 |
| #50 | Softmax Routing Dynamics in Mixture-of-Experts Models: Collapse and Recovery | Shengze Xu, Maolin Deng, Tieyong Zeng | cs.LG | 2026-10-29 |