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.
[abs]Learning to See Through Language: An Exploration of Language Modeling's Effect on Visual RepresentationsMark Endo, Shiye Su, Yuhui Zhang et al.3.67
[abs]Git Context Controller: Manage the Context of Agents by Agentic GitJunde Wu, Minhao Hu, Jiayuan Zhu et al.3.67
[PDF]DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video DifferencesYankai Yang, Yancheng Long, Bin Wen et al.3.67
[abs]Exact Unlearning via Quantized Sufficient StatisticsAmi Tavory, Shripad Gade, Tal Sarig et al.3.67
[abs]Constrained Modulatory Reservoirs for Context-Dependent ComputationSejeung Choi, Minji Jung, Jinyeong Park et al.3.67
[abs]DART: Domain-Agnostic Residual Transfer for Generalist Anomaly DetectionMuhammad Aqeel, Maham Nazir, Marco Cristani et al.3.67
[abs]From Click Imitation to Transition Equivalence: Rethinking Supervision for GUI AgentsZhiming Lin, Tianxiang Xu, zizhao zhang et al.3.67
[abs]Gauge-Symmetric Dual Lagrangian Frameworks for Born-Oppenheimer Molecular DynamicsSungwoo Park, Jongwon Lee, Jiwoong Kim et al.3.67
[PDF]Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear ProbingValentina Njaradi, Clémentine Dominé, Rachel A Swanson et al.3.67
[PDF]PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona RepresentationsRui Xu, yinghui xu, Libo Wu3.67
[abs]Mind the Gap: The Divergent Rebound Dynamics of Diffusion and Autoregressive ModelQiwen Jin, Zhengyu Zhou, Weiwei Liu et al.3.67
[PDF]Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMsVincent-Daniel (Juyoung) Yun, Junhyuk Jo, Sai Praneeth Karimireddy et al.3.67
[abs]Mesh-Free Convolution: Learned Spectral Attenuation and TransportNiloufar Zakariaei, Manav Manav, Eldad Haber3.67
[abs]Beyond FLOPs: Train-Full, Deploy-Partial Multi-Exit Inference via Selective Lightweight IC EnsembleBitchan Eom, Eunchan Kim3.67
[abs]CARD: Internalizing Expert Critique into Reinforcement Learning for Deep SearchYanyu Zhu, Hoilam Pao, Zhaoyu Hu et al.3.67
[abs]Temperature Guidance For Robust Reward Conditioning In Diffusion PlanningJohannes V Busch, Roberto Calandra3.67
[abs]Safe in Its Own Words: Self-Guided Safety Alignment for Multimodal Reasoning ModelsAdeel Yousaf, Souradip Chakraborty, Mubarak Shah et al.3.67
[PDF]Clustered Randomized Smoothing for Stochastic Prediction FunctionsEduardo Figueiredo, Frederik B Mathiesen, Julian F Schumann et al.3.67
[abs]Act, Validate, Adapt: Closing the Causal Discovery-Control LoopTaqiya Ehsan, Shuren Xia, Jorge Ortiz3.67
[PDF]Learning Where It Matters: Geometric Anchoring for Robust Preference AlignmentYoungjae Cho, Jongsuk Kim, Ji-Hoon Kim3.67
[abs]Exploring Multi-Order Self-Similarity for Motion UnderstandingManjin Kim, Heeseung Kwon, Karteek Alahari et al.3.67
[abs]EpiStream: Utility-Aware Temporal Abstraction for Dense-Action StreamsKaize Tan, Ran Zhang, Feng Yichao et al.3.67
[PDF]History-Aware Conformal Prediction Sets for Censored Time-to-Event OutcomesYuyao Wang, Alexander W Levis, Shu Yang et al.3.67
[PDF]Reasoning with Sampling: Cutting at Decision PointsFelix Zhou, Anay Mehrotra, Quanquan C Liu3.67
[abs]RepoScope: Bridging Physical Structure and Logical Flow for Intent-Driven Repository DocumentationZezhou Yang, Chaozheng Wang, Hailiang Huang et al.3.67
[PDF]INSPO : Unlocking Intrinsic Self-Reflection for LLM Preference OptimizationYu Li, Tian Lan, Zhengling Qi3.67
[PDF]Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware SettingsMarie Generali Lince, Vincent Divol, Rémi Flamary et al.3.67
[abs]Action-Level Behavior Policy Optimization for Variance-Reduced Policy GradientsJingkai Huang, Qinxun Bai, Zhengyuan Zhou3.67
[abs]3A-VLA: Abstraction-Aligned Action Learning for Vision-Language Agents in 3D Game WorldsZheyuan Zhou, Liang Du, Zixun Sun et al.3.67
[PDF]FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video UnderstandingKangcong Li, Peng Ye, Lin Zhang et al.3.67
[PDF]Privately Estimating Monotone Statistics in Polynomial TimeGavin R Brown, Ephraim Linder, Mahbod Majid et al.3.67
[PDF]Kernel Selection is Model Selection: A Unified Complexity-Penalised Approach for MMD Two-Sample TestsYijin Ni, Xiaoming Huo3.67
[PDF]Finite Resources False Discovery Rate Control on Structured Hypothesis SpacesBinyamin Perets, Shie Mannor3.67
[abs]UniForm: Segment-Aware GRPO for Joint Punctuation Restoration and Inverse Text NormalizationJunhao Gong, Weiwei Li, Rilin Chen3.67
[abs]Does Cross-Panel Pretraining Transfer Under Marker Heterogeneity? A Large-Scale Empirical Study in Clinical Flow CytometryZixin Zhuang, Benjamin Mashford, Dan Andrews3.67
[abs]Information-Theoretic Generalization for Set-Input Optimization-Valued ObjectivesFutoshi Futami, Masahiro Fujisawa3.67
[abs]Disentangled Multimodal Learning for Scalable Dynamic IR-Drop AnalysisYihan Wen, Su Zheng, Tianshu Hou et al.3.67
[abs]K-prop: Deep Online Learning by Backpropagating Temporal KernelsBingkun Liu, Paul Haider, Federico Benitez et al.3.67
[abs]Mobility Helps Learning: Unsupervised Model Adaptation for Object Recognition via MovementYanan Ma, Yihang Tao, Zhengru Fang et al.3.67
[PDF]Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited ImagesJunhee Lee, JeonDongHyeon, Taeoh Kim et al.3.67
[PDF]Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic PerturbationsHanwei Zhang, Tianma Hu, Gaojie Jin et al.3.67
[abs]HALO: Heterogeneous-Aware LoRA Optimization via Rank Allocation and Client-Aware ProjectionXiaoHua Feng, Yuyuan Li, Jiayuan Fang et al.3.67
[abs]Retrieve-then-Rerank Inference for Vocabulary-Based End-to-End DrivingHyunjun Kim, Donggue Kim, Kichun Jo3.67
[PDF]Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action ModelTao Lin, Yuxin Du, Jiting Liu et al.3.67
[PDF]RoPEMover: Depth-Aware Object Relocation via Positional EmbeddingsIpek Oztas, Duygu Ceylan, Aybars B Aksoy et al.3.67
1 If this project is interesting to you, reach out at [email protected].