NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of NeurIPS 2026
Abstract
The safe for work edition of acceptodds: the submissions, without the markets. Search them, browse them on a map laid out by what they are about, follow the ones you care about, keep reading lists with your group, and get recommendations from what you read. There are no odds, no bets and no reputation here. acceptodds is not affiliated with any organisation or institution. acceptodds is an open source project, open to contributions, at github.com/PotentialHedge/acceptodds-sfw.1 Follow for updates on X.
[PDF]Visual-Advantage On-Policy Distillation for Vision-Language ModelsRuiqi Liu, Xiaolei Lv, Gengsheng Li et al.4.33
[abs]AsdaKV: Attention-Overlap Driven Semantic KV Retrieval for Long-Context LLMsTianming Yan, Kun Yang, Tingwang You et al.4.33
[PDF]Improved Baselines with Representation AutoencodersJaskirat Singh, Boyang Zheng, Zongze Wu et al.4.33
[PDF]Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic ManipulationYifan Xie, YuAn Wang, Guangyu Chen et al.4.33
[PDF]Sampling-Based Safe Reinforcement LearningLuca Vignola, Bruce D Lee, Manish Prajapat et al.4.33
[abs]SkillCIR: Intent-Guided Skill Composition for Training-Free Composed Image RetrievalYuanmin Tang, Lin Li, Yang Du et al.4.33
[PDF]LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model AveragingPeter Richtarik, Yassine Maziane, Ammar Mahran et al.4.33
[abs]GPU Hierarchy Meets Structured Matrices: Fast Algorithms for State-Space ModelsBerlin Chen, Caitlin Wang, Aakash Sunil Lahoti et al.4.33
[PDF]MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-offShuxin Liu, Di Gao, Ou Wu4.33
[PDF]Data-Constrained Language Model Pretraining: Improved Regularization and Scaling LawsZhiwei Xu, Shihao Wu, Hanseul Cho et al.4.33
[abs]Progressive Signal Calibration for Medical Image Segmentation: Diagnosing and Correcting Structural Misalignment in Training SignalsXinyan Zhao, Haijing Liu, Zhuan Cui et al.4.33
[abs]SemISP: Semantic-Consistent Diffusion for Cross-Camera RAW-to-sRGB GenerationZhe Pang, Haina Qin, Ziyu Feng et al.4.33
[PDF]Activation Steering of Video Generation Models via Reduced-Order Linear Optimal ControlJihoon Hong, Alice Chan, Qiyue Dai et al.4.33
[abs]Learning to Commit: Next-Commit Prediction via Online Supervised Contrastive ReflectionMo Li, Qitai Tan, Kai Chen et al.4.33
[abs]ClusQuant: Mitigating Outliers with Clustering-Based Representations for Low-Precision LRMsXingyu Liu, Xiangyang Yin, Tianhua Xia et al.4.33
[abs]Beyond Generation: Unlocking Discriminative Representations from Diffusion ModelsHaowen Cui, Ge Wu, Shuo Chen et al.4.33
[PDF]Dynamic Resolution Routing for Efficient Egocentric GroundingHuixin Sun, Wangbo Zhao, Fanyue Wei et al.4.33
[PDF]SGD at the Edge of Stability: The Stochastic Sharpness GapFangshuo Liao, Afroditi Kolomvaki, Anastasios Kyrillidis4.33
[abs]Visual Reinforcement Fine-Tuning via Bootstrapped Medical ReasoningYequan Bie, Peng Xie, Zhixuan CHEN et al.4.33
[abs]BitShift-RoPE: Zero-FLOP Relative Positional Encoding for Spiking Neural Network TransformersSeung-Kyu Hong, Sangheum Hwang, HYUK-YOON KWON4.33
[abs]Progressive Pseudo-label Self-balancing Towards Unsupervised Vision-Language Models AdaptationSi Qin, Yaxin Hou, Jiawei Tang et al.4.33
[PDF]LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RLYujin Kim, Namgyu Ho, Sangmin Hwang et al.4.33
[PDF]Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent MemoryJingwei Sun, Jianing Zhu, Jiangchao Yao et al.4.33
[abs]STEER: Route-Aware Adaptive Reasoning for Autonomous DrivingYANGANG ZOU, Pei Liu, Nan Song et al.4.33
[abs]Budget-Conditioned Clipping Policies for Differentially Private Federated LearningHao Zhou, SiQi Cai, Hua Dai et al.4.33
[abs]When Does Flow Matching Help Deterministic Multimodal Prediction: A Spatial Transcriptomics StudyHaoran Xu, Wei Yuan, Xiao Han4.33
[PDF]DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language ModelsXinrui Shi, Kai Liu, Ziqing Zhang et al.4.33
[PDF]HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent EnhancementYiyang Cai, Nan Chen, Rongchang Xie et al.4.33
[PDF]Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it DeservesJonas Knupp, Jan Metzen, Jeremias Bohn et al.4.33
[PDF]COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly DetectionJINWOO PARK, Hyeongwon Kang, Seung H Han et al.4.33
[PDF]Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAPJiaan Han, Junxiao Chen, Yanzhe Fu4.33
[PDF]Grokking or Glitching? How Low-Precision Drives Slingshot Loss SpikesLIU Hanqing, Jianjun Cao, Yuanze Li et al.4.33
[PDF]LangFlow: Continuous Diffusion Rivals Discrete in Language ModelingYuxin Chen, Chumeng Liang, Hangke Sui et al.4.33
[PDF]SCALECUA : Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RLBowen Lv, Xiao Liu, Yanyu Ren et al.4.33
[abs]InfCLIP: Unified Data Valuation for CLIP Pretraining via Influence-Inspired ScoringNohyun Ki, Hye Won Chung4.33
[abs]LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA CompositionThamirawaran Sathiyalogeswaran, Navindu De Silva, Chamikara Siriwardane et al.4.33
[abs]STAR-Math: Multi-Agent Mathematical Reasoning under Persistent Meta-Strategic SupervisionJiaao Wu, Xian Zhang, Hanzhang Liu et al.4.33
[PDF]Visual-ERM: Reward Modeling for Visual EquivalenceZiyu Liu, Shengyuan Ding, Xinyu Fang et al.4.33
[PDF]Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and ApplicationsSifan Yang, Danyue Li, Lijun Zhang4.33
[abs]Reasoning Gestures: LLM-Inferred Communicative Functions for Co-Speech Gesture GenerationPinxin Liu, Haiyang Liu, Yunlong Tang et al.4.33
[abs]MDK-MoE: Multi-view Decomposed Kalman Mixture of Experts Framework for Non-stationary Time Series ForecastingRui Hou, Yao Liu, Ruilin Jiang et al.4.33
[abs]Breaking the Second Barrier: Sub-Second Timestamped Omni-Modal CaptioningZhihe Yang, Xin LI, Hao Tan et al.4.33
[abs]Positional Encoding Is All You Need For Scalable Equivariance Constraint RelaxationHagay Michaeli, Haggai Maron, Daniel Soudry4.33
[PDF]DELTA-TTS: Adapting Autoregressive Model into a Diffusion Language Model for Text-to-SpeechJunwon Moon, Yejin Lee, Seungbeom Kim et al.4.33
[PDF]Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion TransformersBozhou Li, Yushuo Guan, Haolin Li et al.4.33
1 If this project is interesting to you, reach out at [email protected].