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]Auto-Dreamer: Learning Offline Memory Consolidation for Language AgentsChongrui Ye, Yuxiang Liu, Yu Wang et al.4.33
[abs]Beyond 3 Million Tokens: A Multi-Modal Foundation Model for Full-Resolution HeliophysicsSujit Roy, Johannes Schmude, Ata A Asanjan et al.4.33
[PDF]On the Complexity of Preference-Based BanditsAhmed Ben Yahmed, Marc Abeille, Clément Calauzènes4.33
[abs]Rethinking Knowledge Distillation for Diffusion Language ModelsYuxuan Sun, Yuanjian Xu, Jianing Hao et al.4.33
[abs]Uncovering the latent structure of interwoven population and temporal codesZachary Friedenberger, Yiwei Cao, Richard Naud4.33
[abs]Split-RL: Local Conflict Resolution in Reinforcement LearningBenjamin Fuhrer, Chen Tessler, Gal Dalal4.33
[PDF]CRAFT: Conflict-Resolved Aggregation for Federated TrainingZiqi Wang, Qiang Liu, Nils Thuerey4.33
[abs]GPA: General Principled Framework for Linearizing Softmax Attention via KV Cache Approximationwang ning, Zekun Li, Tongxin Bai et al.4.33
[PDF]Intrinsically Interpretable Attention via Sparse Post-TrainingFlorent Draye, Anson Lei, Hsiao-Ru Pan et al.4.33
[abs]Multi-Agent Coordination via Support-Preserving DistillationSangmin Lee, Youngju Na, Chanmi Lee et al.4.33
[PDF]Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of UnityZhongjie Shi, Wenjing Liao4.33
[abs]SDHilb: Schrödinger Dynamics-Guided Neural Network with Adaptive Multi-Scale Hilbert Transform for Time Series ForecastingCaihua He, Weiyang Ding4.33
[PDF]Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM AgentsZiming Li, Jiatan Huang, Xiaoguang Guo et al.4.33
[abs]Aligning MLLMs with the Latent Structure of Human Cognition via Behavior-Derived Semantic DimensionsNing E, Changde Du, Yizhuo Lu et al.4.33
[PDF]Is Backpropagation Optimal? When Synthetic Gradients Improve Sample EfficiencyYibo Jacky Zhang, Zeyu Tang, Sanmi Koyejo4.33
[abs]Theoretical guarantees for Banded Approximations of Gaussian ProcessesOmar Kassi, Bernhard Stankewitz, Botond Szabo4.33
[abs]Expert-guided Bayesian optimization for sustainable protein formulationAnna Thomas, Georgios Zaverdinos, Petros Mandalis et al.4.33
[PDF]Statistical Convergence of Spherical First Hitting Diffusion ModelsSimon Bienewald, Lukas Trottner4.33
[PDF]SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video GenerationXu Zhang, Yu Lu, Ruijie Quan et al.4.33
[abs]Principled Policy Optimization for LLMs via Self-Normalized Importance SamplingHuiyang Shao, Xintong Zhang, Junyi Liu4.33
[PDF]SENSE: Semantic Neural Speech Synthesis from Brain Dynamics via Spatial Graph EncodingJisoo Park, Seonghak Lee, Hyojin Park et al.4.33
[PDF]OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligencefeilong tang, Xiang An, Yunyao Yan et al.4.33
[PDF]Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with TransformersJuncheng Dong, Moyang Guo, Bowen He et al.4.33
[PDF]Attention Drift: What Auto-Regressive Speculative Decoding Models LearnDoğaç Eldenk, Payal Mohapatra, Yigitcan Comlek et al.4.33
[PDF]MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision SupportYusuf Kesmen, Fay Elhassan, Jiayi Ma et al.4.33
[PDF]NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUsHojeong Lee, Si H Lee, Sungwon Woo et al.4.33
[PDF]M2A: Synergizing Mathematical and Agentic Reasoning in Large Language ModelsJunJian Wang, Xin Zhou, Qiran Xu et al.4.33
[abs]DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation LearningYuxiang Zeng, Kun Xie, Yang Wang et al.4.33
[abs]AdaTree: Serving-Aware Adaptive Tree Construction for Speculative DecodingSoohyun Cha, Jungi Lee, Jaewoong Sim4.33
[abs]Fisher information and the geometry of memorization in neural networksDaniel Bernstein, Chase Goddard, Luca Di Carlo et al.4.33
[abs]Seeing Both the Forest and the Trees: Reusing Holistic 3D Priors for Part-Decomposed GenerationYiqun Zhao, Binbin Huang, Haobin Duan et al.4.33
[PDF]Neglected Free Lunch from Post-training: Progress Advantage for LLM AgentsChangdae Oh, Wendi Li, Seongheon Park et al.4.33
[PDF]SimSD: Simple Speculative Decoding in Diffusion Language ModelsJunxia Cui, Haotian Ye, Runchu Tian et al.4.33
[abs]LLMs Optimizing LLMs: Automated MegaKernel Generation for Inference AccelerationWeiqiang Xiong, Shaohui Peng, Wenyi Li et al.4.33
[abs]Exact Combinatorial Optimization for Partial Permutation SynchronizationMohammad Mahdi Omati, Arash Amini4.33
[abs]Covariate-Adjusted Deep Causal Learning for Heterogeneous Panel Data ModelsGuanhao Zhou, Yuefeng Han, Xiufan Yu4.33
[abs]Mixture of Layers: Dynamic Layer Routing for Visual ReasoningJeonghwan Kim, Sofia Stoica, Jiwan Chung et al.4.33
[abs]Gradient Boosted Trees for Retrieval-Augmented GenerationHuaiyu Qin, Chunyu Wei, Yueguo Chen et al.4.33
[PDF]Assign and Add: A Mechanistic Study of Compositional ArithmeticBrady Exoo, Alberto Bietti, John Sous4.33
[abs]BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State UpdatesLijian Li, Yuanpeng He, Yudian Zheng et al.4.33
[abs]Dual-Granularity Learning for Regression with Continuous Noisy LabelsHui GUO, Boyu Wang, Grace Yi4.33
[PDF]A Comprehensive View of Fairness through Distributional StabilityGayane Taturyan, Charlotte Laclau, Stephan Clémençon4.33
[abs]CS-DICE: Offline Reinforcement Learning with Coherent Occupancy RegularizationJeremías Figueiredo Paschmann4.33
[abs]RobustPruner: Decoupled Relevance and Uncertainty for Efficient Visual Token Pruning in MLLMsHanwei Zhu, Junhan Fu, Xi Zhang et al.4.33
[abs]Do We Really Need Diffusion for Generative Object Detection? A Minimal Prototype PerspectiveYu Hong, Xiaosong Jia, Yihan Wang et al.4.33
[PDF]Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model UsageShahinul Hoque, Jinghuai Zhang, Jinyuan Stella Sun et al.4.33
1 If this project is interesting to you, reach out at [email protected].