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]Winning the Symmetry Lottery: Learning Invariance from Data Augmentations with TransformersEduardo Santos-Escriche, Valerie Engelmayer, Ya-Wei Eileen Lin et al.4.33
[PDF]Why Do Time Series Models Need Long Context Windows?Luca Butera, Giovanni De Felice, Andrea Cini et al.4.33
[PDF]An Õptimal Differentially Private PAC Learner for Concept Classes with VC Dimension 1Chao Yan4.33
[abs]Who Wrote This Paper? Autonomous Scientific Discovery for 3DGS ResearchSeemandhar Jain, Manmohan Chandraker4.33
[PDF]CoT-Guard: Small Models for Strong MonitoringNirav Diwan, Han Wang, Berkcan Kapusuzoglu et al.4.33
[PDF]M-plicits: Neural Implicit Surfaces via Nested Multiscale ResidualsVinícius Da Silva, Isabelle R de Melo, Matheus Levy de Lima Bessa et al.4.33
[PDF]CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion ModelsZhenghao He, Guangzhi Xiong, Boyang Wang et al.4.33
[PDF]Flexible Routing via Uncertainty DecompositionCharlotte Peale, Siddartha Devic, Parikshit Gopalan et al.4.33
[PDF]DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test TimeZiqi Ma, Hongqiao Chen, Georgia Gkioxari4.33
[PDF]Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP ScenarioFlorentin Coeurdoux, Grégoire Ferré, jean-philippe bouchaud4.33
[PDF]RECIPE: Procedural Planning via Grounding in Instructional VideoLuigi Seminara, Antonino Furnari, Lorenzo Torresani4.33
[abs]Learning to Search, Searching to Learn: A Closed-Loop Framework for Large-Scale Vehicle RoutingYongji Fu, Yi Zhou, Gaojie Jin et al.4.33
[PDF]Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D GenerationJiantao Lin, Meixi Chen, Yingjie Xu et al.4.33
[abs]Relaxed On-Policy Distillation: Selective Credit Allocation for Scaling Reasoning EfficientlyJongwoo Ko, Sara Abdali, Young Jin Kim et al.4.33
[abs]AdKnob: Ad Intensity Control and Labeling for LLM-Native AdvertisingWoo Jae Kim, Seongho Keum, Joonsung Jeon et al.4.33
[abs]Emergent Misalignment as Data-Mediated TransferBaris Askin, Muhammed Ustaomeroglu, Anupam Nayak et al.4.33
[PDF]Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image EditingYuxiao YE, Haoran He, Fangyuan Kong et al.4.33
[PDF]Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature EffectsVasilis Gkolemis, Loukas Kavouras, Dimitrios Kyriakopoulos et al.4.33
[abs]Online Quantile Omniprediction for Proper LossesHyunsuk Kim, Isaac Gibbs, Michael Mahoney et al.4.33
[abs]Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language ModelsImad-Eddine Marouf, khalid OUBLAL, Enzo Tartaglione et al.4.33
[abs]FlowMoP: Stochastic Multi-Person Motion PredictionAadya Agrawal, Ho Kei Cheng, Alex Schwing4.33
[abs]MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene RegulationKangjie Zheng, Amirhossein Vahidi, Liying Jin et al.4.33
[PDF]Economy of Minds: Emerging Multi-Agent Intelligence with Economic InteractionsZhenting Qi, Ao Qu, Huangyuan Su et al.4.33
[abs]SAGE: Semantic Ambiguity Guided Capacity Expansion for Retrieval-Augmented GenerationXunlei Chen, Jinyu Guo, Yi Gong et al.4.33
[PDF]DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous DrivingChen Shi, Jinrui Xu, Shaoshuai Shi et al.4.33
[abs]Imagine, Don't Narrate: The Generative Bottleneck in World Models of Interaction DynamicsDaniel Platnick, Marjan Alirezaie, Hossein Rahnama4.33
[abs]RAGBoost: Robust Tabular Learning via Retrieval-Augmented and Ancillary-Guided Gradient BoostingJinlin Wang, Zhixuan Chen, Qi Ma4.33
[PDF]SeeSE3: The Emergence of 3D Space in Vision FeaturesViorica Patraucean, Leonidas Guibas, Sayna Ebrahimi et al.4.33
[PDF]Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary NetworksEvan G Smith, Bashima Islam4.33
[abs]Bridging Safety and Performance in Autonomous Systems using Offline Reinforcement LearningMumuksh Tayal, Manan Tayal, Ravi Prakash4.33
[PDF]Quasi-Linear ICA for Motor Unit Decomposition during Dynamic ContractionsAlexander K Clarke, Dimitrios Chalatsis, Agnese Grison et al.4.33
[abs]Feed-Forward 3D Gaussian Splatting for High-Fidelity Animatable Hand Avatar Reconstruction from a Single ImageChanho Kim, Kyeonghwan Gwak, Muhammad Salman Ali et al.4.33
[abs]SearchV: Evolutionary Fine-Grained Visual-Token Skipping for Efficient Vision-Language ModelsXinrui Chen, Zhen Huang, Shuwei Li et al.4.33
[abs]From Likelihood Convergence to Parameter Convergence in POMDPsJack Zhang, Saurabh Amin, Jiawei zhang et al.4.33
[abs]Velocity Ambiguity Profiles: Time-Resolved Bayes-Risk Diagnostics for Flow MatchingYunpeng Mei, Xiaowen Zhu, Chenyu Wang et al.4.33
[abs]Skill-Adaptive Noise Scheduling for Diffusion PoliciesWoo Kyung Kim, Gwangpyo Yoo, Eunyoung Park et al.4.33
[abs]Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed TrainingAnshu Raina, Peyman Razaghi, Yuankai Chen et al.4.33
[abs]Unveiling Entropy-Performance Decoupling in Agentic RL for Tool-Integrated ReasoningYirong Zeng, Shen You, Yufei Liu et al.4.33
[PDF]MARS: Enabling Autoregressive Models Multi-Token GenerationZiqi Jin, Lei Wang, Ziwei Luo et al.4.33
[PDF]Gym-Anything: Turn Any Software into an Agent EnvironmentPranjal Aggarwal, Graham Neubig, Sean Welleck4.33
[PDF]Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics EmulationKaihui Cheng, Zhiqiang Cai, Wenkai Xiang et al.4.33
[abs]Open-Ended Scientific Discovery and the Social Dynamics of Evolving Agent NetworksTennison Liu, Silas Ruhrberg Estévez, Rob Davis et al.4.33
[PDF]Nexus: Same Pretraining Loss, Better Downstream Generalization via Common MinimaHuanran Chen, Huaqing Zhang, Xiao Li et al.4.33
[abs]How Can SignSGD Outperform SGD? A Functional Scaling Law PerspectiveZilin Wang, Binghui Li, Jia-Nan Wang et al.4.33
[abs]Efficient Collaborative LLM Fine-Tuning over Heterogeneous Mobile Devices via Many Backbones to One Side-Network TuningXingke Yang, Liang Li, Sicong Li et al.4.33
[abs]Affine-invariant Cubic Newton with Weak LearnersNikita Zozoulenko, Daniel Falkowski, Thomas Cass et al.4.33
1 If this project is interesting to you, reach out at [email protected].