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]Reducing Credit Assignment Variance via Counterfactual Reasoning Pathsfei ding, Yongkang Zhang, youwei wang et al.4.20
[abs]BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric EnvironmentsGe Qu, Jinyang Li, Xiaohan Xu et al.4.20
[abs]A Doubly Smoothed Decentralized Stochastic Minimax Optimization AlgorithmXinwen Zhang, Chiu C Tan, Haibin Ling et al.4.20
[PDF]When Does Interaction Help? Representational Tradeoffs in Value-Based Imitation LearningLuca Viano, Antoine Moulin, Audrey Huang et al.4.20
[PDF]Differentiable Knapsack and Top-k Operators via Dynamic ProgrammingGermain Vivier-Ardisson, Michael E Sander, Axel Parmentier et al.4.20
[abs]Reward Is Not a Universal Interface for Generative Reinforcement LearningVictor Shea-Jay Huang, Poodar Chu, Hongsheng Li4.20
[PDF]From Matrix Inversion to Constraints: Provably Tighter Confidence Regions for Importance Weights in Label ShiftMushan Li, Kihyun Han, Yanyuan Ma4.20
[abs]Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning SegmentationJun Huang, zhangjunyang, Zijie Yue et al.4.00
[abs]RRL-HOI: Reflective Reinforcement Learning for Open-Vocabulary HOI DetectionYongchao Xu, Jiawei Liu, Junfeng Wang et al.4.00
[abs]LessMimic: Versatile Humanoid-Object Interaction with Unified Distance Field RepresentationsYutang Lin, Jieming Cui, Yixuan Li et al.4.00
[abs]MolSpecFlow: Modality-Incomplete Molecular–Spectral Learning for MS/MSYu Wang, Fan Yang, Kaikun Xu et al.4.00
[PDF]SteerVTE: Seamless Video Text Editing with Style and Glyph ControlKai Zeng, Moran Li, Zhengwei Wang et al.4.00
[abs]Scaffold3D: SfM-Conditioned Pointmap Prediction for Multi-View 3D ReconstructionFrano Rajič, Yutong Chen, Haofei Xu et al.4.00
[PDF]RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero RemappingYuzong Chen, Xilai Dai, Jake Hyun et al.4.00
[PDF]Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type DeconvolutionDmytro Rizdvanetskyi, Nathan Roos, Pavlo Lutsik4.00
[abs]Nonlinear Direct Feedback Alignment for Scalable Backpropagation-Free TrainingWu Lin, Yan Fan, Chenxiang Ma et al.4.00
[PDF]Intent Factored Generation: Unleashing the Diversity in Your Language ModelEltayeb Ahmed, Uljad Berdica, Martha Elliott et al.4.00
[PDF]Towards Unified Dynamic Face Landmark DetectionSebastian Regalado Lozano, Varshanth R Rao, Ruowei Jiang et al.4.00
[abs]Bridging Graph Worlds: Neural Approximation of Gromov-Wasserstein DistancesDong Qiao, Chris Ding, Jicong Fan4.00
[abs]WsiSSM: A Weakly Supervised Subset-Matching Framework for Unified Classification and Segmentation of Histopathology Whole Slide ImagesGuangjian Zeng, Siyuan Tao, Chengzhi Zhao et al.4.00
[abs]Sparse blind deconvolution via thresholded Wirtinger flowMengting Chen, Haitong Lan, Ziping Zhao4.00
[abs]PhysDNet: Physics-Driven Gradient Amplification for Real-Time Image DehazingRayen Dhahri, Lei Sun, Victor J Morinigo et al.4.00
[PDF]Rethinking Training Targets, Architectures and Data Quality for Universal Speech EnhancementSzu-Wei Fu, Rong Chao, Xuesong Yang et al.4.00
[PDF]PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-VideoJunseong Shin, Hyeonsu Jo, Daehyun Kim et al.4.00
[abs]RiSE: Residual Subspace Expert for Generalizable Text-Centric Image Forgery LocalizationKahim Wong, Kemou Li, Yiming Chen et al.4.00
[abs]Mind the Parameters: Lightweight and Efficient Brain Visual Decoding with Shared Tensor CoresHaodong Jing, Panqi Yang, Rongchao Zhang et al.4.00
[abs]From Ideas to Code: Tree-structured Policy Optimization for Automated Algorithm Design with LLMsRui Zhang, Ping Guo, Liyong Lin et al.4.00
[PDF]Adaptive Coordinate Transforms for Neural OperatorsChaoyu Liu, Zhonghao Li, Gaohang Chen et al.4.00
[PDF]Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion ModelsTaesung Kwon, Jonghyun Park, Hyungjin Chung et al.4.00
[PDF]GRAPHLCP: Structure-Aware Localized Conformal Prediction on GraphsPeyman Baghershahi, Fangxin Wang, Debmalya Mandal et al.4.00
[abs]ROLLVERIFY: BRIDGING EFFICIENCY AND ACCURACY IN LONG-TAIL ROLLOUT REINFORCEMENT LEARNINGYongqiang Yao, Jingru Tan, Kaihuan Liang et al.4.00
[PDF]PointForward: Feedforward Driving Reconstruction through Point-Aligned RepresentationsCheng Chi_, Xianqi Wang, Hongcheng Luo et al.4.00
[abs]MaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space ModelsSyed Ibrahim Omer, Ginny Wong, Xiangyu Zhao4.00
[abs]Conflict-Suppressed RAG: A Simple Decoding-Time Framework for Faithful Retrieval-Augmented GenerationYuanye Xu, Yuting Wang, Linyi Guo et al.4.00
[abs]BRAVO: Bridge Matching for Autoregressive Video GenerationShihua Zhang, Zhenxiong Tan, Xinchao Wang4.00
[abs]Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image CaptioningYuanze Hu, Zhichao Yang, Junwei Jing et al.4.00
[PDF]Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstructionkejun ren, Lei Jin, Tianxin Huang et al.4.00
[PDF]A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language ModelsHamid Kazemi, Atoosa Malemir Chegini, Maria Safi4.00
[PDF]Learning to Persuade Exposes How Easily LLMs Abandon Correct BeliefsNimet Beyza Bozdag, Emre Can Acikgoz, Gokhan Tur et al.4.00
[abs]Spike-to-Field Mechanisms of Turbulence-Like Dynamics in Spatial Spiking Neural NetworksZequan Liu4.00
[PDF]Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement LearningWo Wei Lin, Ethan Rathbun, Enrico Marchesini et al.4.00
[PDF]UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World ModelingBoyu Chen, Yi Chen, Lu QIU et al.4.00
[abs]Propagate to Discover: Graph-Structured Propagation for Generalized Category Discoveryyongqi tian, Junyong Liu, Jinkun Ran et al.4.00
[abs]NeuroNTP - A Generalizable Multimodal Foundation Model for EpilepsyJózsef Kovács, Amadeus Hauser, Gudrun Gröppel et al.4.00
[PDF]Exposing the Illusion of Erasure in Knowledge Editing for LLMsAdvik Basani, Anshuman Chhabra4.00
[abs]Adaptive multiscale operator correction via learned spectral subspace and physics-informed optimization.Subham Patel, Himanshu Pandey, RATIKANTA BEHERA4.00
[PDF]Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet VideoZihui Gao, Ke Liu, Jiawang Bian et al.4.00
1 If this project is interesting to you, reach out at [email protected].