| 1 | Rethinking Neural Thickets Without Weight Perturbations | Nicolas Dufour, Elouan Gardès, Amil Dravid +2 | cs.LG | 2026-10-29 |
| 2 | Rethinking Pre-pretraining | Alexander Stern, Tim Rocktäschel, Acyr Locatelli +1 | cs.CL | 2026-10-29 |
| 3 | EditAgent: Rethinking Agentic Image Editing | Haiyang Xu, Tianyu Wang, Jialu Li +5 | cs.CV | 2026-10-29 |
| #4 | Rethinking GFlowNet Training: Negative Reinforce Dynamics | Pedro Dall'Antonia, Daniel Csillag, Diego Mesquita | cs.LG | 2026-10-28 |
| #5 | Rethinking LLM Jailbreak Evaluation: Continuous Risk Landscapes Beyond Binary Outcomes | Yukai Zhou, Wenjie Wang | cs.LG | 2026-10-28 |
| #6 | Representing the Unseen: Rethinking Visual Imagination for Spatial Reasoning | Zengqi Zhao, Zun Wang, Shoubin Yu +2 | cs.CV | 2026-10-27 |
| #7 | Does Your Generalist Skill Optimizer Really Incentivize Agentic Tasks? Rethinking Skill Optimization via Bipartite Attribution | Jiawei Zhou, Bo Peng, Yuxuan Huang +4 | cs.AI | 2026-10-27 |
| #8 | RankFormer: Rethinking Time Series Transformers through Representation Capacity Analysis and Progressive Decoding | Peiwang Tang, Cheng HE, Xijie Liang +1 | cs.LG | 2026-10-27 |
| #9 | Satellite Intelligence: Distributed Training, Collaborative Inference,and LLM Adaptation in LEO Constellation | Zheng Lin, Zhanwei Wang, Yuxin Zhang +9 | cs.NI | 2026-10-26 |
| #10 | SoK: Timestamps Are Not a Time Model: Rethinking Temporal Reasoning in Host-Based Intrusion Detection | Rene Heinzl, Markus Nissl | cs.CR | 2026-10-26 |
| #11 | Quality over Quantity: Rethinking Data and Model Assumptions for Bengali Coreference Resolution | Zenith Biswas, Andrew Thomas Dyer | cs.CL | 2026-10-26 |
| #12 | Rethinking Evaluation for Principled Generalization Using a Kripkean Challenge to Meaning as Use | Niyar R Barman, Omar Naim, Nicholas Asher | cs.CL | 2026-10-26 |
| #13 | Rethinking Data Imbalance in Class Incremental Surgical Instrument Segmentation | Shifang Zhao, Long Bai, Kun Yuan +8 | cs.CV | 2026-10-26 |
| #14 | Good Rankings, Poor Choices? Rethinking Language-Only Vision-Language Model Selection | Hyuk Kwon, Jaebyeong Jeon, Hyeonseo Jang +1 | cs.CV | 2026-10-26 |
| #15 | Rethinking Verification in Agent Harnesses | Zhengxin Zhang, Erkang Zhu, Yin Lin +3 | cs.AI | 2026-10-25 |
| #16 | Rethinking Retrieval in the Long-Context Era: Training-Free Semantic Trees for Adaptive Context Construction | Zhe Xu, Tianhao Liao, Zhenqing Ling +3 | cs.CL | 2026-10-25 |
| #17 | Whispers from the Neighbors: Rethinking Caption Consensus as Inference-Time Evidence for Vision-Language Retrieval | Khang Nhat Hoang Vo, Belal Shoer, Abhirama Subramanyam Penamakuri | cs.CV | 2026-10-24 |
| #18 | Refined Assessment for Translation Evaluation: Rethinking Machine Translation Evaluation in the Era of Human-Level Systems | Dmitry Popov, Vladislav Negodin, Ekaterina Enikeeva +3 | cs.CL | 2026-10-24 |
| #19 | Rescuing Your Pruning: Rethinking Visual Token Pruning and Post-Training Recovery in MLLMs | Peiran Yin, Hao Wu, Zihao Yang +3 | cs.CV | 2026-10-24 |
| #20 | Rethinking Microscopy Generation: Co-Designed Diffusion for Biologically Interpretable Single-Cell Synthesis | Shumpei Takezaki, Duway Nicolas Lesmes-Leon, Ryoma Bise +4 | cs.CV | 2026-10-24 |
| #21 | Rethinking LoRA Initialization for Robust Asymmetric Learning Rates | Disen Liao, Yaoliang Yu | cs.LG | 2026-10-23 |
| #22 | Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data | Joonhyeok Jeong, Jy-yong Sohn, Kibok Lee | cs.LG | 2026-10-23 |
| #23 | Rethinking Sequence Compression with Test-time Regression | Sihan Yang, Jie Huang, Hanxuan Li +4 | cs.LG | 2026-10-22 |
| #24 | Rethinking Fisher Vectors for Second-order Multi-scale Deep Feature Aggregation in Scalable Scene Retrieval | Alexy Bhowmick, Sarat Saharia, Shyamanta M. Hazarika | cs.AI | 2026-10-22 |
| #25 | Rethinking the Evaluation of LLM Fact-Checkers | Ayana Niwa, Miyu Yamada, Kouta Nakayama +3 | cs.CL | 2026-10-21 |
| #26 | Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy | Riteng Zhang, Xiaoqian Wang | cs.LG | 2026-10-21 |
| #27 | Rethinking Video Autoencoders for Interactive World Models | Adrien Ramanana Rahary, Yutong Bai, Nicolas Dufour +2 | cs.CV | 2026-10-21 |
| #28 | EPIC: Rethinking Trust Regions for Autoregressive LLM Policies via Exact-KL Prefix Importance-Ratio Clipping | Chengxi Li, Hanlin Wu, Zhicheng Cai +4 | cs.LG | 2026-10-21 |
| #29 | Rethinking Post-hoc Debiasing of Large Pretrained Models | Divyaansh Mertia, Chirag Bhutra, Himanshu Shekhar +2 | cs.CV | 2026-10-21 |
| #30 | Rethinking Underwater Image Enhancement: Learning through Text-Guided Degradation Curriculum | Hongri Tian, Wenxue Li, Tian Ye +6 | cs.CV | 2026-10-21 |
| #31 | Rethinking Agentic Model Orchestration for Time Series Forecasting | Tong Guan, Tianxiang Zhan, Shirui Pan +1 | cs.LG | 2026-10-21 |
| #32 | Rethinking Time Series Tokenization from a Frequency Perspective | Zelong Tian, Ming Jin, Bo Du +1 | cs.LG | 2026-10-20 |
| #33 | Model Exposure on One Device Endangers Others: Rethinking Edge Neural Network Security across Devices | Yuyang Zhang, Kangjie Chen, Yihui Jin +1 | cs.CR | 2026-10-19 |
| #34 | Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation | Minseong Kim, Jongbok Won, Jeesup Park +2 | cs.LG | 2026-10-19 |
| #35 | Rethinking BPE: Merge Selection as Model Selection | Vijini Liyanage, François Yvon | cs.CL | 2026-10-19 |
| #36 | Rethinking Sparse-View 3D Gaussian Splatting: A Few-Shot Learning Perspective on Overfitting Prevention | Lejia Ye, Bin Wu, Jingjing Gao +2 | cs.CV | 2026-10-19 |
| #37 | Rethinking EEG Spatial Super-Resolution as Dynamic State Decomposition and Filtering | Hongjun Liu, Leyu Zhou, Chang Ge +2 | cs.AI | 2026-10-17 |
| #38 | Rethinking the design space of Vanilla Pixel Diffusion Transformers | Soumik Mukhopadhyay, Long Mai, Abhinav Shrivastava +1 | cs.CV | 2026-10-16 |
| #39 | Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition | Juho Jung, Seongjae Kang, Jinyoung Han | cs.LG | 2026-10-16 |
| #40 | Not Every Mention Is a Claim: Rethinking Object Hallucination Detection in Vision-Language Models | Hsin-Ling Hsu, Neeraja Kirtane, Kuan-Hao Huang | cs.CV | 2026-10-16 |
| #41 | PONDER: Learning to Generate in the Right Order | Julius Erbach, Dominik Narnhofer, Bernt Schiele +2 | cs.CV | 2026-10-16 |
| #42 | Do Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling | Zehui Feng, Weichuan Wang, Xiaohan Chen +2 | cs.CL | 2026-10-16 |
| #43 | Rethinking GRPO for Large Reasoning Model Safety Alignment | Jiawei Chen, Yi Zhang, Jiawei Du +9 | cs.AI | 2026-10-16 |
| #44 | Rethinking Routing Exploration in Modern Mixture-of-Experts | Bingcong Li, Hao Ma, Michael Muehlebach +2 | cs.LG | 2026-10-15 |
| #45 | Beyond Downstream QA: Rethinking How We Evaluate Agent Memory | Sebastian-Antonio Toma, Jean de Kernier, Mike Ply +1 | cs.CL | 2026-10-15 |
| #46 | Rethinking Successive Rejects Algorithms | Mohamed Khair, Junpei Komiyama | stat.ML | 2026-10-15 |
| #47 | Rethinking the Role of Tool Graph Memory in Multi-Turn Tool Use | Uiji Hwang, Richeng Xuan, Taeuk Kim | cs.CL | 2026-10-15 |
| #48 | Rethinking Classifier-Free Guidance for TI2I Flow Matching | Andreas Floros, Elena Koritska, Teofilo de Campos +4 | cs.CV | 2026-10-15 |
| #49 | Rethinking Learning from Label Proportions via Moment Matching | Tianhao Ma, Wei Wang, Yivan Zhang +4 | cs.LG | 2026-10-15 |
| #50 | Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow | Tinglan Wang, Haixu Liu, Shaobo Chen +4 | cs.LG | 2026-10-14 |