| 1 | Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers | Jiongfan Yang, Weichen Fan, Haiwen Diao +2 | cs.CV | 2026-10-29 |
| 2 | L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory | Jinhyeok Choi, JoungBin Lee, Jongmin Lee +5 | cs.CV | 2026-10-29 |
| 3 | HairDeck: Animation-Ready Stylized Hair Cards from a Single Image | Yuze He, Yixiang Wei, Wang Zhao +3 | cs.CV | 2026-10-29 |
| #4 | Learning developmental dynamics from lineage context | Gokul Gowri, Nic Fishman, William N. Colgan +10 | q-bio.QM | 2026-10-29 |
| #5 | How to Loop Your Transformer: Loop Scaling, Specialization, and Parallel Inference | Chanakya Ekbote, Artidoro Pagnoni, Devendra Singh Sachan +5 | cs.LG | 2026-10-29 |
| #6 | TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents | Guangzhi Wang, Junfu Pu, Yiran Wang +10 | cs.CV | 2026-10-29 |
| #7 | Upcycling Language Models for Multiple Specialized Domains | Mingzi Cao, Xi Wang, Nikolaos Aletras | cs.CL | 2026-10-29 |
| #8 | UniRA: Unified Representation Alignment and Auto-Encoding for Efficient Diffusion Generation | An Lanji, Dawei Liu, Jin Li +3 | cs.CV | 2026-10-29 |
| #9 | ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformer | Wenxi Li, Jingchen Huang, Chenyang Lyu +4 | cs.CV | 2026-10-29 |
| #10 | BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots | Jingchen Huang, Wenxi Li, Chenyang Lyu +3 | cs.CV | 2026-10-29 |
| #11 | TACFormer: Transformer-Based Generative Model for Target-Conditioned De Novo PROTAC Design | Yossra Gharbi, Rocío Mercado | cs.LG | 2026-10-29 |
| #12 | Attention, Dynamic Wave and Hybrid Sequence Mixers in Language Models | Dmytro Babarytskyi, Oleksandr Babarytskyi | cs.LG | 2026-10-29 |
| #13 | AI at a Turning Point: From ChatGPT through Neural Networks to Neuromorphic AI | Volker Kempe | cs.LG | 2026-10-29 |
| #14 | From the Transformer to a Formal Semantics of Coordinated Transformations | Marco Giunti, Fabrizia Giulia Garavaglia | cs.AI | 2026-10-29 |
| #15 | Cross-Encoder Anchor Refinement for Zero-Shot Anomaly Detection | Kaisong Ji, Ziyang Xu, Chang Bian +3 | cs.CV | 2026-10-29 |
| #16 | Transformer-inspired architectures make machine-learned electron densities accurate and transferable enough to bypass self-consistency | Jeheon Woo | physics.chem-ph | 2026-10-29 |
| #17 | AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers | Bin Xu, Mo Zhang, Zhengfeiyang Zhang +6 | cs.CV | 2026-10-29 |
| #18 | FlexTry-On: A Time-Efficient Framework for Multi-Scenario Virtual Try-on | Phuong Dam, Quyen Nguyen Duc, Son Hoang Minh +1 | cs.CV | 2026-10-29 |
| #19 | Emergence of the transformer architecture as the score of entropic laws of random measures | Giacomo Greco | cs.AI | 2026-10-29 |
| #20 | TactoHand: Learning Geometry-Based Dense Hand-Surface Interaction Fields from Video | Ziheng Xi, Weibo Li, Jiayi Yu +6 | cs.CV | 2026-10-29 |
| #21 | ROAD: Modern Adversarial Training for Simple One-Step Distillation at Scale | Xiaoou Li, Shan You, Tao Huang | cs.CV | 2026-10-29 |
| #22 | Regional Anchor Routing for Multi-Object Motion Transfer | Yuze Li, Fuchen Long, Xinlong Sun +3 | cs.CV | 2026-10-29 |
| #23 | Softmax Routing Dynamics in Mixture-of-Experts Models: Collapse and Recovery | Shengze Xu, Maolin Deng, Tieyong Zeng | cs.LG | 2026-10-29 |
| #24 | Multi-Solution Inverse Design of Pixelated Patch Antennas Using an Autoregressive Transformer | Young-Mok Yun, Seung-Won Shin, Jaeyong Chung +1 | cs.LG | 2026-10-29 |
| #25 | WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining | Yuhao Lu, Jiongxu Chen, Hexiang Wei +9 | cs.CV | 2026-10-29 |
| #26 | Seeing and Imagining as One: Unified Video Generation and 4D Perception for Embodied World Modeling | Haitang Feng, Zhuoman Liu, Zhennan Wang +5 | cs.CV | 2026-10-29 |
| #27 | Where Position Matters: Profiling-Guided Layer-Wise RoPE Allocation in Transformers | Zhiwei Liu, Boao Kong, Bing Liu | cs.LG | 2026-10-29 |
| #28 | Joint Rigid Alignment and Morphable Reconstruction from Partial 3D Face Scans | Eli A. Underwood, Nicolas Rondan, Angel V. Peterchev +1 | cs.CV | 2026-10-29 |
| #29 | Kinematic Causal Attribution: Black-Box Explanations of Motion versus Geometry for 4D Point-Cloud Video Models | Zerui Wang | cs.CV | 2026-10-29 |
| #30 | Closed Gates Leak: Decomposing Adjacent-Layer Cancellation in Gated Language Models | Harvey Dam, Ganesh Gopalakrishnan | cs.LG | 2026-10-28 |
| #31 | MCCL: Training Pytorch models across a fleet of Macs at Skywalker Sound | Kevin Sasso, Chris Fiegel, Francis Aitken +2 | cs.DC | 2026-10-28 |
| #32 | Implicit Reasoning in Transformers: Bridging the Compositionality Gap in GPT-2-like Models | Davide Venuto, Leonardo Venuto | cs.CL | 2026-10-28 |
| #33 | AlbumVSR: Identity-Preserving Face Video Super-Resolution from a Personal Photo Album | Nianyao Du, Xijun Wang, Stanley H. Chan | cs.CV | 2026-10-28 |
| #34 | CopyLoop: Fast Looped Transformer Decoding via Context Copying and Shallow Screening | Wenyu Du, Stephen Chung | cs.CL | 2026-10-28 |
| #35 | "Close enough?" An investigation into multiplication errors in LLMs | William Bolton, Bezawit Tilaye, Huw Day | cs.AI | 2026-10-28 |
| #36 | Two-Stage Clipping: Linear-Time Approximate and Exact Mixed-Norm Projections for Transformers | Michel Barlaud, Jean-Paul Marmorat | cs.LG | 2026-10-28 |
| #37 | SpectralTF-MAE: A Pre-trained Spectral Foundation Model for Tokamak Fusion Plasma Diagnostics | Xiao Wang, Zhijie Lu, Duoqing Yang +7 | cs.CV | 2026-10-28 |
| #38 | Leaving the Cave by Breaking the Symmetry: Identifiable Structure Can Enable Cross-Lingual Generalization | Frederick Riemenschneider, Anette Frank | cs.CL | 2026-10-28 |
| #39 | SaiVLA-JEPA: Evaluating Future Latent Prediction in JEPA-Conditioned VLA Control | Rufeng Xiao, Ruihao Xiao, Wei Chen +1 | cs.RO | 2026-10-28 |
| #40 | Vision-Based Density Estimation for Adaptive Traffic Control | Mohammad Usaid, Deepak Silaych, Hrithik Mhatre +1 | cs.CV | 2026-10-28 |
| #41 | Deeper Backpropagation or More Updates? Training Looped Language Models Across Budgets | Jiarun Shen, Xiao Li | cs.CL | 2026-10-28 |
| #42 | Encode Once, Answer Many: Internalizing Context via Parametric Flow | Xinhao Zhong, Mengxuan Wu, Chonghua Liao +22 | cs.AI | 2026-10-28 |
| #43 | ConvRoute-ViT: Convolutional Token Routing for Efficient Vision Transformers | Manish Das, Shiv Ram Dubey, Satish Kumar Singh | cs.CV | 2026-10-28 |
| #44 | Cross Lingual Abstractive Summarization for Marathi | Asang Dani, Shailesh R Sathe | cs.CL | 2026-10-28 |
| #45 | ParaTTT: Parallelizing Test-Time Training Layers with Deep Memories | Noel Loo, Neehal Tumma, T. Konstantin Rusch +3 | cs.LG | 2026-10-28 |
| #46 | HotPOT: Operator Transformer with Heterogeneous Physics Experts for Large-Scale PDE Pre-training | Jiayi Li, Guancheng Zhou, Yisi Luo +5 | cs.LG | 2026-10-28 |
| #47 | Embodied at Sea: Imitation Learning for Multi-Task Underwater Manipulation | Greta Perez-Haiek, Luca Macesanu, Kevin Angers +3 | cs.RO | 2026-10-28 |
| #48 | Replaying the Same Gradients at a Different $\varepsilon$: A Registered Test of the Fixed-Trajectory Account of Adam's $\varepsilon$ for One Rare Row | Lngel Kyo | cs.LG | 2026-10-28 |
| #49 | Post-Training Large Language Models with LLMON | Basel Shbita, Michael Hind, Chad DeLuca +8 | cs.AI | 2026-10-28 |
| #50 | TGTV: An Interpretable Framework for UAV Fault Detection and Traceability via Spatiotemporal Graph Learning and Large Language Models | Zixuan Wang, Changbo Shi, Ji Liu | cs.LG | 2026-10-28 |