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]Measuring and Strengthening Behavioral Suppression in Language ModelsLuxi (Lucy) He, Pengcheng Jiang, Jifan Zhang et al.3.33
[PDF]Diagnosing and Repairing Citation Failures in Generative Engine OptimizationZhihua Tian, Yuhan Chen, Yao Tang et al.3.33
[PDF]Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image FeedbackHuaisong Zhang, Hao Yu, Yuxuan Zhang et al.3.33
[PDF]Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking NetworksAditi Aravind, Konstantinos Ladakis, Mario Alexios Savaglio et al.3.33
[PDF]Epiplexity Guided Data Selection and Generation for Out-of-Distribution GeneralizationEllen Su, Andres Potapczynski, Shikai Qiu et al.3.33
[abs]Clean-Label Poisoning for Gradient-Boosted Decision TreesSinuo Fan, Jun Woo Chung, Weijie Zhao et al.3.33
[abs]Behaving Better, Thinking Worse: Sycophancy Across Post-Training StagesSonnet Xu, Kritika Singh, Sheharbano Jafry et al.3.33
[PDF]From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research AgentsShuoling Liu, Zhiquan Tan, Kun Yi et al.3.33
[PDF]ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor MemoryYurui Chang, Yongkang Du, Yuanpu Cao et al.3.33
[abs]AGiR: Mitigating Gift Over-Reliance in Mixed-Motive GamesWoohyeon Byeon, Seongmin Kim, Jiwon Jeon et al.3.33
[abs]From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt EditorsWentao Ye, Yali Ye, Zhiqing Xiao et al.3.33
[abs]Joint EM Image Super-Resolution and Segmentation with Semantic and Structural PriorsJiateng Shou, Haoyuan Shi, Zhiwei Xiong3.33
[PDF]From Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMsZhentao Tan, Chang Liu, Yao Liu et al.3.33
[PDF]Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?Jingheng Ye, Huiqi Zou, Simon Yu et al.3.33
[abs]GEAR: Generator-Adaptive State Space Models for Associative RecallJun Meng, Mohammadhossein Amouei, Zengyu Lin et al.3.33
[abs]When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object SegmentationValay Mahesh Bundele, Susmit Agrawal, Mehran Hosseinzadeh et al.3.33
[PDF]RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded TransformerShuo Lyu, Jinhao You, Zhuohang Lyu et al.3.33
[abs]Contextual Flow Matching for High-quality Visual Content GenerationBozhi Luan, Hong Chen, Jianmin Bao et al.3.33
[abs]WebSpatial: A Benchmarking Framework of Spatial Intelligence via Web-based Runtime EnvironmentsShaofei Liu, Weichen Bi, Yun Ma3.33
[PDF]Unveiling Memorization–Generalization Coexistence: A Case Study on Arithmetic Tasks with Label NoiseLinyu Liu, Pinyan Lu3.33
[abs]A Characterization of Latent Variable Causal Models Consistent with Observational DataHongshuo Yang, Adiba Ejaz, Yushu Pan et al.3.33
[abs]Subdata Selection: A Unified Framework for Optimal Selection and Statistical Efficiency AssessmentMin Yang, Wei Zheng, John Stufken et al.3.33
[abs]Understanding Multimodal Failure in Action-Chunking Behavioral CloningLorenzo Mazza, Massimiliano Datres, Ariel Rodriguez et al.3.33
[abs]Value-Rectified Distillation for Flow-based Offline Reinforcement LearningKe Jiang, Wen Jiang, Yoshinobu Kawahara et al.3.33
[abs]Efficient and Robust Physical 3DGS-MPM Simulation via Interior Filling and Text-Physics OptimizationYikun Ma, Yiqing Li, Jingwen Ye et al.3.33
[PDF]RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box AgentsSonali Goel, Pranav Vaidhyanathan, Lucas Schorling et al.3.33
[abs]What to Perturb, How to Propagate: A Graph-Guided Transferable Attack on VLP ModelsYongjae Kim, Sungbin Park, Hoon Ji et al.3.33
[abs]MorphoGen: Free-Form XML Evolution for Robot Morphology DesignHongyuan Su, Yu Zheng, Yong Li3.33
[PDF]CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time ScalingYifan Zhang, Yutong Dai, Viraj Prabhu et al.3.33
[abs]SPec: Adaptive Self-Speculative Decoding for Vision-Language ModelsYuqi Huang, Xingyao Li, Yunlong Hou et al.3.33
[PDF]Learning Pareto Stationary Fronts via Single-Pass BackpropagationElina Rojin Celik, Marcos M. Raimundo, Isabel Valera3.33
[PDF]Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning TasksItamar Trainin, Shauli Ravfogel, Omri Abend et al.3.33
[PDF]Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate TrainingPierre Cesar, Sofya Dymchenko, Abhishek Purandare et al.3.33
[PDF]LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video GenerationBo Jiang, Depu Meng, yihan hu et al.3.33
[PDF]LiSA: Lifelong Safety Adaptation via Conservative Policy InductionMinbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra et al.3.33
[PDF]Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to HallucinateHaocheng Ye, Aoting Hu, Xinwei Zhang et al.3.33
[abs]SIGMA: A Sigmoid-Gated Sampler for Test-Time Scaling in Diffusion Language ModelsZiwen Zhang, Weiyu Chen, Yuyan Zhou et al.3.33
[abs]When Does Knowing the State Help? Diagnosing Process vs. Outcome Reward DesignWenpei Shao, Ross Jacobucci3.33
[abs]SLOT-IR: Learning Disentangled Slot Representations for Infrared Spectral UnmixingJingru Gan, Yannah J.U. Melle, Yanqiao Zhu et al.3.33
[PDF]AgentKVShift: Efficient KV Cache Reuse for Agentic Memory SystemsNilesh Prasad Pandey, Jason Kong, Lanxiang Hu et al.3.33
[PDF]Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant MaskingHaoyang Luo, Linwei Tao, Jie Gui et al.3.33
1 If this project is interesting to you, reach out at [email protected].