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]: A Simple Framework for 2D-to-3D RegistrationHao Deng, Xiangtai Yang, Guangmingzi Yang et al.3.67
[PDF]Selectivity and Shape in the Design of Forward-Forward Goodness FunctionsTalha Rüzgar Akkuş, Şuayp T Kocabay, Kamer A Yuksel et al.3.67
[PDF]Aligning Language Models with Selective PredictionGaoxiang Luo, Yifan Wu, Sinian Zhang et al.3.67
[PDF]Align Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation AlignmentLoukas Sfountouris, Giannis Daras, Paris Giampouras3.67
[PDF]Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action ModelsBryce Grant, Xijia Zhao, Peng Wang3.67
[abs]Frank-LoRA: Federated Rank-Aware LoRA for Fine-Tuning Large ModelsSaber Malekmohammadi, Kevin Kuo, Virginia Smith et al.3.67
[PDF]Understanding the Challenges in Iterative Generative Optimization with LLMsAllen Nie, Xavier Daull, Zhiyi Kuang et al.3.67
[PDF]DiPhon: Diffusion on Graphons for Scalable Graph GenerationSergio Rozada, Yiming QIN, Manuel Madeira et al.3.67
[PDF]TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM BacktestingZeyu Zhang, Bradly Stadie3.67
[abs]The Kernel Reality Check: Benchmarking and Distilling Efficient Attention at ScaleFirat Oncel, Cem Subakan, Mirco Ravanelli et al.3.67
[abs]PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue AgentsJian Zhong, Zeyu Liu, Pingchuan Cao et al.3.67
[PDF]Toward Cognitive Supersensing in Multimodal Large Language ModelsBoyi Li, Yifan Shen, Yuanzhe Liu et al.3.67
[abs]BlendCast: Teaching Vision-Language Model to Anticipate Member Skill in Weather EnsemblesTao Han, Fenghua Ling, Dazhao Du et al.3.67
[PDF]Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High DimensionsEUNBEE YOUN, Donghan Kim, Dae W Kim3.67
[PDF]Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language ModelsJaehyun Kwak, Nam Cao, Boryeong Cho et al.3.67
[abs]Decide Before You Record: Heterogeneity-Guided Pre-Acquisition Stimulus Selection for Cross-Day NeuroprosthesesDi Wu, Binglun Huang, Chengxi Xie et al.3.67
[PDF]Autonomous Scientific Discovery via Iterative Meta-ReflectionBingchen Zhao, Sara Beery, Oisin Mac Aodha3.67
[abs]Generalised Linear Models in Deep Bayesian RL with Learnable Basis FunctionsJingyang You, Hanna Kurniawati3.67
[abs]Exploring Advertising Manipulation in Diffusion Image GenerationTianshi Che, Yang Zhou, Yushan Mu et al.3.67
[abs]Calibration Is Not Control: Intervention Advantage for LLM-Agent OversightChubin Zhang, Zhenglin Wan, Xingrui Yu et al.3.67
[PDF]BalCapRL : A Balanced Framework for RL-Based MLLM Image CaptioningShaokai Ye, Vasileios Saveris, Yihao Qian et al.3.67
[PDF]Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature LearningTom Jacobs, Guido Montufar3.67
[abs]BoxTuning: Object-Aware Visual Prompting for Multimodal Model Fine-TuningZekun Qian, Ruize Han, Wei Feng3.67
[PDF]VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement LearningRUIYANG ZHANG, Qianguo Sun, Chao Song et al.3.67
[abs]Generation-for-Understanding with Structured Action Scripts for Embodied Multimodal LearningHange Zhou, Mingzhe Zhang, Hongyu Ge et al.3.67
[abs]Debiasing Sketched Ridge Regression: A Functional Estimation PerspectiveYucong Liu, Florian Schäfer3.67
[PDF]Aligning LLMs with Biomedical Knowledge using Balanced Fine-TuningZhenchao Tang, Fang Wang, Haohuai He et al.3.67
[PDF]Quantile-Coupled Flow Matching for Distributional Reinforcement LearningMichael Groom, Victor-Alexandru Darvariu, Lars Kunze et al.3.67
[abs]From Generic to Dedicated: A Novel Optimizer for Online Continual LearningYongyi Wu, Zheng Wang, Sen Lin3.67
[abs]Structural Entropy Optimized Communication for Multi-Agent Reinforcement LearningWei Du, Benyu Wu, Wei Guo et al.3.67
[abs]ExpertNavigator: Functionally Coherent Expert Grouping and Pairwise-Ranked Routing for High-Fidelity Dense-to-MoE ConversionXiaohan Qin, Cancheng Zhang, Xiaoxing Wang et al.3.67
[PDF]Quantile Geometry Regularization for Distributional Reinforcement LearningZhaofan ZHANG, Minghao Yang, Rufeng Chen et al.3.67
[PDF]Memory Grafting: Scaling Language Model Pre-training via Offline Conditional MemoryRunxi Cheng, Yuchen Guan, Yongxian Wei et al.3.67
[abs]Efficient evaluation and error pattern discovery for blackbox AI systemsMaxim Rabinovich, Harvineet Singh, Aman Sinha3.67
[abs]What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative ModelsKarim Farid, Rajat Sahay, Yumna Alnaggar et al.3.67
[PDF]MoRe: Modular Representations for Principled Continual Representation Learning on Sequential DataJiaqi Sun, Boyang Sun, Rasmy M. H. et al.3.67
[abs]Foveated BagNet: Inherent Interpretability Does Not Exclude Global ContextHolger Heidrich, Sarah Müller, Andreas Schilling3.67
[PDF]Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement LearningYunan Wang, Minghui Song, Zihan Zhang et al.3.67
[abs]Static-Dynamic Disentanglement for Efficient Multi-Frame Vision-Language-Action ModelsWeikang Qiu, Huashuo Lei, Tinglin Huang et al.3.67
[abs]Physics-Constrained Generative World Model for Off-Road Terrain via Post-hoc ProjectionYuan Zhou, Hao Yu, Ruiran Cao et al.3.67
[abs]Blind-Window Forecasting: Real-Time Benchmarking and Multimodal Reconstruction for Tropical CyclonesZhaoran Feng, Xuanhong Chen, Zengbing Chen et al.3.67
[abs]MedVIGOR: Visual Evidence Internalization for Observation-Driven Reasoning in Medical VLMsYuan Wu, Jiayu Qian, Sipeng Wu et al.3.67
[PDF]TensorCommitments: A Lightweight Verifiable Inference for Large Language ModelsOguzhan Baser, Elahe Sadeghi, Eric Wang et al.3.67
[PDF]DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test GenerationHao Liu, Steven Liu, Xin Zhang et al.3.67
[abs]SamaDICE: Safe Multi-Agent Reinforcement Learning with Stationary Distribution Correction EstimationThe Viet Bui, Tien Mai, Thanh Nguyen3.67
[abs]Cardinality-Decomposed Loss for Heterogeneous GNNsParul Maheshwari, Amulya Paruchuri, Alireza Sahami Shirazi3.67
1 If this project is interesting to you, reach out at [email protected].