| 1 | R$^2$-Omni: Reducing Structural and Precision Redundancy in Omni-LLMs for Long-Form Generation | Bolong Feng, Pengfei Zhou, Zhenglin Wan +2 | cs.CV | 2026-11-02 |
| 2 | Lookahead Prediction-Guided Adaptive Visual Refocusing for Interleaved Multimodal Reasoning | Mengzhao Wang, Yanli Ji, Peng Ye | cs.CV | 2026-11-02 |
| 3 | UPSHIFT: User Preference Steering from Human-AI Interaction Feedback Traces | Jingping Wang, Zhanhao Li, Shao Zhang +1 | cs.AI | 2026-11-02 |
| #4 | VerdictAD: Few-Shot Anomaly Detection via Decision-Guided Refinement | Shangquan Sun, Wenjun Luo, Yuanzhi Wang +4 | cs.CV | 2026-11-02 |
| #5 | SYNC: A Training-Free Inference Controller for Dynamic Layer Selection in Multi-Persona Alignment | Yosef Nuraga Wicaksana, Muhammad Reza Qorib, Fadhil Muhammad +1 | cs.CL | 2026-11-02 |
| #6 | Flat Features, Detailed Images? Simple Detail Control for Diffusion Transformers | Qingtao Yu, Zhen Wang, Jiyang Zheng +3 | cs.CV | 2026-11-02 |
| #7 | SVD-Prune: Spectral Vision Token Pruning under Extreme Compression | Yvon Apedo, Martyna Poreba, Michal Szczepanski +1 | cs.CV | 2026-11-01 |
| #8 | Training-Free Motion-Corrected 3D Brain MRI Reconstruction via Event-Guided References | Wei Jiang, Hongli Chen, Tianyi Ding +3 | cs.CV | 2026-11-01 |
| #9 | EarlySelectKV: Anticipatory KV Selection via Cross-Layer Query Proxies | Yuhao Liu, Yuehao Li, Linghe Zhang +4 | cs.CL | 2026-11-01 |
| #10 | Restoring Semantic Fidelity for Training-Free High-Resolution Image Generation in Diffusion Transformers | Junjie Li, Zengbin Wang, Gaoxiang Li +3 | cs.CV | 2026-11-01 |
| #11 | SEALECT: Scene-Conditioned Pose Priors for Plausible Maritime Vessel Retrieval | Faisal Mohammad, Mohamed Younis | cs.CV | 2026-11-01 |
| #12 | Recoverability-Aware Evaluation of Diffusion Video Inpainting and Object Removal | Yanliang Qi, Jiacheng Ding, Cong Guo +1 | cs.CV | 2026-11-01 |
| #13 | Can Large Language Models Extend Their Agentic Capabilities to Goal Pursuit in Open-Ended Multi-Turn Interaction? | Mingyu Chen, Jingkai Lin, Xiaofen Xing +3 | cs.CL | 2026-11-01 |
| #14 | Label-Free Localization and Test-Time Suppression of CLIP's Typographic Circuits | Bohan Liu, Wenqian Ye, Guangzhi Xiong +3 | cs.CV | 2026-11-01 |
| #15 | Resolve, Clear, or Defer: Training-Free Active Prototype Triage for Ecological Detection Pipelines | Anirudh Potlapally, Brijesh Nanda Brunda Yogananda, Jianyang Gu +4 | cs.CV | 2026-11-01 |
| #16 | FOCUS: Closed-Loop Attention Feedback for Efficient Vision-Language Understanding | Akul Santhosh, Aastha Jhunjhunwala | cs.AI | 2026-11-01 |
| #17 | Same Path, Less Time: Training-Free Fast Execution of Vision-Language-Action Models under Inference Latency | Fuyi Chen | cs.RO | 2026-11-01 |
| #18 | J-Anchor: Defending Against Prefill Attacks via J-Space Selective Refusal Restoration | Running Yang, Beidi Zhao, Xiaoxiao Li | cs.CR | 2026-10-31 |
| #19 | StreamClarify: Proactive Clarification for Grounded Streaming Video Question Answering | Zhuchen Shao, Bo Chen, Klara Nahrstedt | cs.CV | 2026-10-31 |
| #20 | QVR3D: Query-Guided Visual Reasoning for Training-Free 3D Grounding | Jung-Hao Kao, Jing-En Huang, Jia-Wei Liao +4 | cs.CV | 2026-10-31 |
| #21 | Jet-QSparse: Accelerating Agentic LLM Inference with 4-Bit Sparse Attention | Haozhan Tang, Hao Kang, Meng Lu +7 | cs.LG | 2026-10-31 |
| #22 | SNAPPerf: Software-Aware Tabular Foundation Model for Retraining-Free Performance Prediction of Configurable Systems | Amine Lbath, Massih-Reza Amini, Vadim Okun | cs.SE | 2026-10-31 |
| #23 | What Helps Denoising Can Hurt Memory: Rethinking History in Long Video Generation | Yubin Jing, Ziyang Zhang, Meng Chen +3 | cs.CV | 2026-10-31 |
| #24 | Training-free Conditional Object Composition for Multi-object Image Generation with Diffusion Models | Hsuan-Fu Wang, Hsuan-Tien Lin | cs.CV | 2026-10-31 |
| #25 | ConstraintMatch: Compositional Image-Text Matching through Constrained Regional Evidence Selection | Yuhong Zhou, Yubo Gao, Xiangbo Shu | cs.CV | 2026-10-31 |
| #26 | SceneBound: How Much Should a Streaming 3D Reconstruction Model Remember? | Ziming Wang, Chuyue Gong, Chutian Wang +4 | cs.CV | 2026-10-31 |
| #27 | SAVIER: Source-Anchored Visual Inspection and Evidence-Guided Repair for Vietnamese Cultural Text-to-Image Generation | Gia-Huy Thai, Duc-Tien Khong, Trung-Nghia Le | cs.CV | 2026-10-31 |
| #28 | Density-Aware Calibration for Resource-Efficient Medical Vision-Language Models | Tien-Dat Dam, Huu-Thuan Huynh, Minh-Triet Tran +1 | cs.CV | 2026-10-31 |
| #29 | Content-Preserving Principal Feature Blending for Training-Free Style Personalization | Le-Hoang Bui, Hoang-Nguyen Cao, Trung-Nghia Le +2 | cs.CV | 2026-10-31 |
| #30 | RATR: Training-Free Material Rebinding via Role Assignment and Temporal Routing | Jiehui Tang, Yunlong Yu, Zhao Wang +1 | cs.CV | 2026-10-31 |
| #31 | Agentic Context Management for Multi-Turn Human-AI Conversations | Matthew Ho, Chenglong Wang, Baolin Peng +5 | cs.AI | 2026-10-31 |
| #32 | RangeSWA: Training-Free Length Extrapolation for Continuous Diffusion Language Models | Guangfu Guo, Xiaoqian Lu, Linsey Pang +4 | cs.CL | 2026-10-30 |
| #33 | Any Forcing: Any-Step Generality and One-Step Stability for Autoregressive Video Generation | Jiahua Xu, Yijie Fang, Nannan Wang +6 | cs.CV | 2026-10-30 |
| #34 | Trainable Vector Quantization for Large Language Models | Anastasiia Prutianova, Alina Bogdanova, Mikhail Shutov +3 | cs.LG | 2026-10-30 |
| #35 | DIFFNAS: Predictor-Free Neural Architecture Search via Diffusion Model and Zero-Cost Evaluation | Yize Sun, Hanzhang Ma, Zixin Wu +3 | cs.LG | 2026-10-30 |
| #36 | Attention Maps Know When to Think: Training-Free Difficulty-Aware Chain-of-Thought for Reasoning Segmentation | Chanseul Cho, Jaesung Jun, Dongheon Lee +1 | cs.CV | 2026-10-30 |
| #37 | Verify--Backtrack Loop: Structured Precondition Recovery for Long-Horizon Language Agents | Mingyang Liu, Qingcan Kang, Shixiong Kai +4 | cs.AI | 2026-10-30 |
| #38 | VoxLution: Evolving Voxels for High-Fidelity 3D Scene Generation | Daoyi Gao, Xinyi Zhang, Alexey Bokhovkin +2 | cs.CV | 2026-10-30 |
| #39 | When Links Mislead: Label-Free Structural Polarity for Zero-Shot Classification of Web Pages | Hanshuai Cui, Zhiqing Tang, Zhi Yao +2 | cs.LG | 2026-10-30 |
| #40 | Parse Before You Execute: Efficient Spatial Reasoning with Executable Primitives | Xiwei Liu, Yulong Li, Xinling Zhuang +5 | cs.CV | 2026-10-30 |
| #41 | What We Keep of What We Forget: Replacement Operators and Routing Semantics in Training-Free MoE Expert Pruning | Ezza Ali, Sehrish Bibi, Momina Moetesum +1 | cs.LG | 2026-10-30 |
| #42 | In-Model Context Compression with Agentic Soft Tokens for Long-Horizon LLM Agents | Xuning He, Kai Fan, Runyu Zhang +4 | cs.CL | 2026-10-30 |
| #43 | Rethinking Neural Thickets Without Weight Perturbations | Nicolas Dufour, Elouan Gardès, Amil Dravid +2 | cs.LG | 2026-10-29 |
| #44 | RADIOlogy: A Single-Pass Approach to Training-Free Zero-Shot Anomaly Detection | Joaquín Figueira, Giacomo D'Amicantonio, Egor Bondarau | cs.CV | 2026-10-29 |
| #45 | Hierarchical Step Decomposition for Training-free Online Video Step Grounding | Long Zhou, Luca Zanella, Paolo Rota +2 | cs.CV | 2026-10-29 |
| #46 | Neural Blind Deconvolution for Image Scanning Microscopy | Eliot Guez, Nathan Buskulic, Lisa Cuneo +2 | cs.CV | 2026-10-29 |
| #47 | KARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising Agents | Xinhua Miao, Yuanzhen Rong, Weiru Zhang +1 | cs.AI | 2026-10-29 |
| #48 | AegisFlow: Training-Free Non-Myopic Path-Safe Guided Flow Matching | Kunpeng Liu, Boshi Zhang, Keyou You | cs.AI | 2026-10-29 |
| #49 | GROME: GROunding Factorized MEmory into Video World Models | Fang Yu, Xiaoxue Wu, Haiyu Zhang +6 | cs.CV | 2026-10-29 |
| #50 | Can AI Agents Interface Clinicians and Complex Models? | Giulio Colombini, Matteo Falcioni, Mario Massimo +5 | cs.MA | 2026-10-29 |