| 1 | TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races | Tom Sander, Pierre Fernandez, Itai Gat +11 | cs.CR | 2026-10-29 |
| 2 | On the Fundamental Limits of Prefill-Based Decoding Length Prediction | Haowen Shi, Xuzhe Yan, Fahao Chen +1 | cs.AI | 2026-10-29 |
| 3 | Fast and accurate neural triage decoding of ultra-high-rate quantum LDPC codes | Hong-Ye Hu, Zhenlai Wang, Binzhao Luo +2 | quant-ph | 2026-10-29 |
| #4 | How to Loop Your Transformer: Loop Scaling, Specialization, and Parallel Inference | Chanakya Ekbote, Artidoro Pagnoni, Devendra Singh Sachan +5 | cs.LG | 2026-10-29 |
| #5 | 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 |
| #6 | Latent Prediction Yields Cross-Subject Alignable Representations in Sensory-Evoked fMRI | Serwan Jassim, Victoria Bosch, Daniel Anthes +2 | cs.LG | 2026-10-29 |
| #7 | Spectral Invariant Fusion and Refinement for Domain Generalized Semantic Segmentation | Yansong Bai, Yunzhi Zhuge, Xinzhuo Yu +4 | cs.CV | 2026-10-29 |
| #8 | KV Cache Quantization for Diffusion Language Models | Yan Tai, Yunan Ding, Guangzhao Li +5 | cs.CL | 2026-10-29 |
| #9 | DWISE: Denoising Workload-Informed Scheduling Engine | Lie Li, Wen Li, Junxiao Shen +2 | cs.LG | 2026-10-29 |
| #10 | The Importance of Speech Genre for End-of-Turn Detector Training | Rini Sharon, Kadri Hacioglu, Jeena Prakash +1 | eess.AS | 2026-10-29 |
| #11 | BEACON: Distilled Begin/End-Aware Structured Decoding for Continuous Sign Language Segmentation | Guohou Zhang, Kalin Stefanov | cs.CV | 2026-10-29 |
| #12 | End-to-End Guarantees for Masked Diffusion Models under Conditional Mixing | Fareed Sheriff | cs.LG | 2026-10-29 |
| #13 | Decoding Geometry, Not Tokens: Efficient VLMs for Robot Affordance and Trajectory Prediction | Akila Ayanthi, Darshana Priyasad, Tharindu Fernando +4 | cs.RO | 2026-10-29 |
| #14 | Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models | Chengwei Zhou, Zhaoyan Jia, Massoud Pedram +1 | cs.CL | 2026-10-29 |
| #15 | Unlimited OCR Works 2 | Shu Wei, Jingjing Wu, Qunyi Xie +9 | cs.CL | 2026-10-29 |
| #16 | ACAM-J-MARS: Multi-Atlas Riemannian Spectral Representations for Decoding Advanced Meditation States from fMRI | Jian Wang, Winson F. Z. Yang, Wugeng Zheng +1 | cs.LG | 2026-10-29 |
| #17 | CLaW: Codec-Guided Adaptive Latent Watermarking for Traceable Diffusion Image Generation | Huangchao Song, Lingyun Yu, Cong Li +3 | cs.CV | 2026-10-29 |
| #18 | Why Speculative Decoding Works Better Than Predicted on Sparse MoE Models | Ekagra Ranjan, Komal K. Teru, Bharat Venkitesh +1 | cs.LG | 2026-10-28 |
| #19 | TableTune: Measured, Self-Correcting Draft-Length Tables for Dynamic Speculative Decoding | Abhishek Malvankar, Paul Castro, Nick Mitchell +1 | cs.ET | 2026-10-28 |
| #20 | Structural-Test Geometry as an Inductive Bias for Partially Observable World Models | Todd Y. Zhou | cs.LG | 2026-10-28 |
| #21 | CopyLoop: Fast Looped Transformer Decoding via Context Copying and Shallow Screening | Wenyu Du, Stephen Chung | cs.CL | 2026-10-28 |
| #22 | Learning Scientific Trajectories to Predict Future Biomedical Discoveries | Chia-Hsuan Chang, Brian Ondov, Jiang Lv +7 | cs.CL | 2026-10-28 |
| #23 | What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty | Hazel H. Kim, Jakub Binkowski, Ekaterina Fadeeva +22 | cs.CL | 2026-10-28 |
| #24 | Recurrent Bipartite Graph Neural Networks for QC-MDPC Error Decoding in McEliece Cryptosystems | Parth Rajeshkumar Tandel, Elisabeth Fink | cs.CR | 2026-10-28 |
| #25 | Automatic Iconographic Annotation of Medieval Illuminations: Comparing Generative Vision-Language Models and Supervised Discriminative Classifiers | Vincent Jolivet, Lucas Terriel, Chahan Vidal-Gor{è}ne | cs.CV | 2026-10-28 |
| #26 | SparseTokenGS: Gaussian-based Sparse-View CBCT Reconstruction via Reusable Token Pool | Zihan Deng, Zhenzhen Gong, Yujie Liu +10 | cs.CV | 2026-10-28 |
| #27 | Multi-Token Prediction Done Right | Jayden Teoh | cs.LG | 2026-10-28 |
| #28 | ParaTTT: Parallelizing Test-Time Training Layers with Deep Memories | Noel Loo, Neehal Tumma, T. Konstantin Rusch +3 | cs.LG | 2026-10-28 |
| #29 | Answer-Only Disclosure: Private-Context LLM Assistance over Web APIs with a Leakage Ledger | Liang Yuan, Xiaohu Du, Ruikun Luo +6 | cs.CR | 2026-10-28 |
| #30 | Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI | NVIDIA, :, Aastha Jhunjhunwala +556 | cs.CL | 2026-10-28 |
| #31 | Frequency-Adaptive Gaussian Grids for Efficient Image Representation | Anatolii Evdokimov, Stavros Diolatzis, Bingxuan Li +3 | cs.CV | 2026-10-27 |
| #32 | Merge and Branch: Efficient Tree-Structured Supervised Fine-Tuning of LLMs for Recommendation | Yunqin Zhu, Yao Xie | cs.IR | 2026-10-27 |
| #33 | Statistical Detection of Positional Bias in LLM-Based Recommender Systems: Methodologies and Empirical Evidence | Carlos Peláez-González, Francisco Herrera, Andrés Herrera-Poyatos | cs.IR | 2026-10-27 |
| #34 | FAD-KV: Adaptive Dictionary KV Caching for Efficient Reasoning Decoding | Yuxuan Zhu, David H. Yang, Parisa Shiravani +5 | cs.CL | 2026-10-27 |
| #35 | Multi-Draft On-Policy Distillation for Diffusion Drafters | Petr Molodyk, Yuchen Zhu, Jaemoo Choi +2 | cs.CL | 2026-10-27 |
| #36 | Metacognitive Decoding: Efficient Inference for Diffusion Language Agents | Mingyu Zhao, Shuhang Lin, Ligong Han +5 | cs.CL | 2026-10-27 |
| #37 | Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data | Geunhyoung Kim, Sung Ju Hwang | cs.LG | 2026-10-27 |
| #38 | TopoField: Technical Report for ECCV 2026 SceneFun3D Challenge | Zhiwei Chen, Zhiheng Fu, Zixu Li +3 | cs.CV | 2026-10-27 |
| #39 | TDLM: Adaptive Temporal Integration for Diffusion Language Models | Bohang Sun, Max Zhu, Francesco Caso +3 | cs.LG | 2026-10-27 |
| #40 | HiLo-RD: Cross-Budget Self-Distillation for Masked Diffusion Language Models | Xiang Li, Chengting Yu, Jungang Li +5 | cs.LG | 2026-10-27 |
| #41 | GUI-JEPA: Candidate-Conditioned JEPA Latents as a Fast Action Policy for Mobile GUI Agents | Bingchao Wang, Yongcheng Jing, Shunyu Liu +5 | cs.AI | 2026-10-27 |
| #42 | When All Rollouts Fail: Policy-Compatible Joint Decoding for Hard-Problem Reasoning | Zehao Wang, Hanzhu Chen, Runquan Gui +2 | cs.LG | 2026-10-27 |
| #43 | Variable-Length Feedback Coding With Universal Decoding and Bandit Channel Selection | Recep Can Yavas | cs.IT | 2026-10-27 |
| #44 | API-TAIL: Detecting Model Substitution in LLM APIs through Temperature-Aligned Likelihood Tails | Haocheng Mei, Yuchuan Tian, Ye Yuan +4 | cs.LG | 2026-10-27 |
| #45 | The Vocabulary Is Already Here: Adapting Pretrained Interpretable Features for Generative Recommendation | Ziluowen Luo, Ruochen Liu, Jun Yin +6 | cs.IR | 2026-10-27 |
| #46 | Neuronal Identity as an Organizational Basis for Analyzing Neural Population Dynamics | Seungjae Han, Joshua Yedam You, Soi Kim +5 | q-bio.NC | 2026-10-27 |
| #47 | RankFormer: Rethinking Time Series Transformers through Representation Capacity Analysis and Progressive Decoding | Peiwang Tang, Cheng HE, Xijie Liang +1 | cs.LG | 2026-10-27 |
| #48 | Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs | Donghyeon Cho, Joowon Kim, Seungho Shin +1 | cs.CV | 2026-10-27 |
| #49 | Balanced State Subspaces for Mamba-2 State Compression | Shang Tingyu, Cao Wenfei | cs.LG | 2026-10-27 |
| #50 | Learning to Formalize: Bridging Open-Ended Workloads and Fast Decision Models | Chengxuan Pei, Ziyao Wang, Teng Mei +1 | cs.AI | 2026-10-27 |