| 1 | Latent Reasoning in Continuous Space for Unified Multimodal Models | Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee +2 | cs.CV | 2026-10-30 |
| 2 | Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention | Ales Kubicek, Andrea Caciolai, Liangzu Peng +7 | cs.AI | 2026-10-30 |
| 3 | A Better Critic Matters for Distribution Matching Distillation | Zongze Wu, Xianbang Wang, Zhengyang Geng +5 | cs.CV | 2026-10-30 |
| #4 | ACCT: Asymmetric Cross-LLM Context Transfer | Yuzhe Liu, Haolin Tian, Tonghan Wang | cs.AI | 2026-10-30 |
| #5 | Subquadratic Attention with a Hierarchical Tree-Structured Indexer | Leon Lufkin, Cutter Dawes, Alexander Speicher +3 | cs.CL | 2026-10-30 |
| #6 | Rethinking Asymmetry in Self-Supervised 3D Geometry Learning | Gyeongjin Kang, Freeman Cheng, Botao Ye +3 | cs.CV | 2026-10-30 |
| #7 | RangeSWA: Training-Free Length Extrapolation for Continuous Diffusion Language Models | Guangfu Guo, Xiaoqian Lu, Linsey Pang +4 | cs.CL | 2026-10-30 |
| #8 | The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results | Omer Asim Ozturk, Cihan Aydiner | cs.AI | 2026-10-30 |
| #9 | GhostPrefix: Synchronization-Free Universal Prefix Attacks for ASR Manipulation | Shengding Liu, Ashwin Innuganti, Qiben Yan | cs.LG | 2026-10-30 |
| #10 | TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish | Ahmet Tuğrul Bayrak, Fatma Nur Korkmaz, Nur Yağmur Tuncer +1 | cs.CL | 2026-10-30 |
| #11 | GeoFlip: Benchmarking Geometry-Sensitive Physics in Video Generation | Yuqi Li, Junming Liu, Bowen Hu +4 | cs.CV | 2026-10-30 |
| #12 | Less Loss, Fixed Weights: Logit Corrections for Forgetting | Hanyu Yang | cs.LG | 2026-10-30 |
| #13 | SecPO: Principled Adversarial Training for Prompt Injection Security | Sizhe Chen, Yibo Peng, Jaewon Chang +2 | cs.CR | 2026-10-30 |
| #14 | DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention | Zhangchi Feng, Harry Jiang, Yangyifei Luo +2 | cs.AI | 2026-10-30 |
| #15 | TwinPast: Benchmarking Historical Evidence Use in Streaming Video Understanding with Evidence Contrastive Video Pairs | Haotian Yang, Yong Chen, Cheng Peng +4 | cs.CV | 2026-10-30 |
| #16 | Chronos-2: A foundation model for multivariate time series forecasting | Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken +22 | cs.LG | 2026-10-30 |
| #17 | Structure-Aware Skill Retrieval and Arbitration for Optimization Modeling | Anran Liu, Benzhao Hou, Zongsheng Cao +3 | cs.AI | 2026-10-30 |
| #18 | Automated Keyword Generation Using LLMs in a High-Volume Data Virtualization Service | Saiful Khan, Yiwen Xing, Joyraj Chakraborty +4 | cs.AI | 2026-10-30 |
| #19 | How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces | Donghang Duan, Qingyu Liu, Yifei Liu +3 | cs.CR | 2026-10-30 |
| #20 | Text as an Index for Zero-Shot Cross-Domain Knowledge Tracing | Yin Yi, Haiping Ma, Siyu Song +2 | cs.CL | 2026-10-30 |
| #21 | Movens-Zero: Scaling Humanoid Motion Foundation Models with Large-Scale Human Videos | Wendong Bu, Tinghong Ye, Qizhou Wang +21 | cs.RO | 2026-10-30 |
| #22 | SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI | Van Bach Nguyen, Qianli Wang, Nils Feldhus +2 | cs.CL | 2026-10-30 |
| #23 | Dynamical Memory Transformer: Selective Recurrent Memories with Constant Cost Attention | Yannis Bendi-Ouis, Xavier Hinaut | cs.AI | 2026-10-30 |
| #24 | Open-Weight MLLMs Cannot Compare What They Cannot Name | Wenxin Su, Anna Kreshuk | cs.CV | 2026-10-30 |
| #25 | ObjectGuidedMap: An Object-Aware Model for Robust Bird's Eye View Map Prediction in High-Occlusion Scenarios | Christian Bohn, Harsh Yadav, Klaus Friedrichs +2 | cs.CV | 2026-10-30 |
| #26 | PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization | Hanqiao Ye, Yuzhou Liu, Mengqi Rong +3 | cs.CV | 2026-10-30 |
| #27 | RECAST: REconstruction of Chain-of-Thought via Auditable Structured Traces | Qi Wang, Kang Xu, Chengcheng Wan +1 | cs.AI | 2026-10-30 |
| #28 | What Standard Evaluations Hide About Detectors of Hijacked LLM Agents: Rare Attacks, Unseen Tools and Benchmark Transfer | Mahmoud Abbasi, Juan M. Núñez V., Amin Shahraki | cs.CR | 2026-10-30 |
| #29 | Whose Values, Which Contexts, and What Signals? Grounding Cultural Value Alignment with Re3Culture | Jing Yao, Hyunjin Hwang, Weihua Zheng +12 | cs.AI | 2026-10-30 |
| #30 | Clinical-Protocol-Aware Cyber Resilience for Connected Clinical Technologies Under AI-Enabled Adversarial Conditions | Pranav Patel, Siva Kannathasan, Prerak Patel +3 | cs.AI | 2026-10-30 |
| #31 | Multimodal In-Context Learning with Explicit Rule Induction | Yuquan Li, Xinyang Jiang, Yuhao Xue +1 | cs.AI | 2026-10-30 |
| #32 | Latent-Lens: Visual Perception in Small Language Models Through Latent Communication | Mo Shahdloo, Faegheh Sardari, Mathew Salvaris | cs.LG | 2026-10-30 |
| #33 | Do LLMs Know When They Are Wrong About Molecules? In-Context Property Prediction with Self-Reported Uncertainty | Matthias Busch, Marius Tacke, Tamadur Albaraghtheh +5 | cs.LG | 2026-10-30 |
| #34 | Task Vectors Can Be Linearly Decomposed into Interpretable and Controllable Components | Yukiya Horiba, Hakaze Cho, Takahiro Yakoh | cs.LG | 2026-10-30 |
| #35 | Advancing Clinical Trial Outcome Prediction with Domain-Specific Large Language Models | Burak Bakkar, Hana Moalla, Mohamed Salem Jedidi +2 | cs.AI | 2026-10-30 |
| #36 | GraphNIAH: A Benchmark for Long-Context Reasoning over Real-World Graphs | Minh-Nam Tran, Abulhair Saparov | cs.CL | 2026-10-30 |
| #37 | When Steering Shifts Discourse: Identifying and Intervening on Discourse-Level Changes due to Activation Steering in LLMs | Shivam Adarsh, Hetianyu Huang, Lau Safin +2 | cs.CL | 2026-10-30 |
| #38 | Enhancing Medical Lesion Segmentation via Several Simple Modules | Ruichen Li, Zhao Yao | eess.IV | 2026-10-30 |
| #39 | Co$^2$ODE: Conditionally Coarse-Grained Model Discovery for Rewiring in Biochemical Networks | Theodore de Pomereu, Fabian Fröhlich | q-bio.QM | 2026-10-30 |
| #40 | GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning | Chanseul Cho, Noori Bae, Dongheon Lee +1 | cs.CV | 2026-10-30 |
| #41 | What Carries Architectural Signal? A Code-to-Architecture Mapping Study | Rakhshanda Jabeen, Morgan Ericsson, Yuyao Duan +1 | cs.SE | 2026-10-30 |
| #42 | What Should LLMs Forget: Reinforcement Unlearning of Knowledge Associations | Wutong Xu, Yun Qu, Haiyan Feng +2 | cs.AI | 2026-10-30 |
| #43 | DrawSplat: Atlanta World-Guided Implicit Gaussian SLAM for Indoor Reconstruction | Fan Zhu, Zhisong Xu, Ziyu Chen +2 | cs.CV | 2026-10-30 |
| #44 | BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion | Ruurd J. A. Kuiper, Robert A. Bagheri | cs.CL | 2026-10-30 |
| #45 | Verify--Backtrack Loop: Structured Precondition Recovery for Long-Horizon Language Agents | Mingyang Liu, Qingcan Kang, Shixiong Kai +4 | cs.AI | 2026-10-30 |
| #46 | CEFR Level Assessment across Languages and Text Granularities | Eugene Matsumura, Yuki Arase | cs.CL | 2026-10-30 |
| #47 | Enhancing Knowledge Entity Relation Extraction in Abstracts and Full-text Content of Academic Articles Using Large Language Models | Yingyi Zhang, Chengzhi Zhang | cs.CL | 2026-10-30 |
| #48 | TACO: Trajectory-Aware Curvature Observation for Memorization Localization and Mitigation in Diffusion Models | Ruxi Gu, Zilei Wang, Wei Wang | cs.CV | 2026-10-30 |
| #49 | Enhancing Sentiment Classification on Small Datasets through Data Augmentation and Transfer Learning | Mahmoud S. Mayaleh, Samer A. Mayaleh | cs.LG | 2026-10-30 |
| #50 | Infinite ResNets are Gaussian Mean ODEs | Louis-Pierre Chaintron, Lénaïc Chizat, Javier Maass | cs.LG | 2026-10-30 |