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]From Representation to Intervention: Using Emotion Vectors to Monitor and Guide Language ModelsGeorgia Dimaki, Martin Villanueva Dimakis4.00
[PDF]Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble SelectionYigit Turkmen, Baturalp Buyukates, Melih Bastopcu4.00
[abs]The Bayesian Learning Rule Beyond KL GeometrySOPHIA SKLAVIADIS, Wu Lin, Mario Figueiredo et al.4.00
[abs]Efficient One-to-many Domain Translation via Diffusive Entropic Optimal TransportDavid Vaneev, Ivan Shchekotov, Denis Rakitin et al.4.00
[PDF]ADAPT: Hybrid Prompt Optimization for LLM Feature VisualizationJoão N. Cardoso, Arlindo L Oliveira, Bruno Martins4.00
[abs]Less is More: Fewer Tokens and Blocks Make AIGI Detection Faster and More GeneralizableHaipeng Fang, Yixing Lu, Yu Li et al.4.00
[abs]Learning Hierarchical Forward Processes For Discrete Diffusion Language ModelsInhyeok Jeong, Jeongwhan Choi, Jaehyeon Park et al.4.00
[abs]One Avatar, Any Budget: Robust LoD for Dynamic Gaussian AvatarsHaoyu Zhao, Wenjuan Gong, Junang Qi et al.4.00
[abs]SCHTs: A Semi-Structured Dynamic Sparse Training Framework for Hardware-Efficient Deep LearningYuan Hua, Zhaoxu Ding, Jilin Zhang et al.4.00
[PDF]Externalized CPDAG Summaries Improve LLM Causal DeductionWentao Sun, João P Nogueira, Dominique Verchere et al.4.00
[abs]Humanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward GatingHaozhuo Zhang, Qiang Zhang, Jian Tang et al.4.00
[abs]CPA: Efficient and Stable FP4 RL Training via Cross-Precision AlignmentGu Gong, Yining Wei, Yuechen Tao et al.4.00
[PDF]EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal GroundingGeo Ahn, Jiwook Han, Youngrae Kim et al.4.00
[PDF]Distilling Sequential Computation in Transformer Language ModelsZixuan Lan, Jessica Yang, Yanhong Li et al.4.00
[abs]Cross-Distribution Generalization in Longitudinal Behavioral Data Through Frozen Coherence ConstraintsAhatsham Hayat, Mohammad Hasan4.00
[PDF]Breaking : Cooperative Policy Optimization Improves Diverse LLM ReasoningHaoxuan Chen, Tianming Liang, Wei-Shi Zheng et al.4.00
[PDF]CENDRe: Concept Extraction with Natural Domain RepresentationsAntonia Holzapfel, Andres Posada Moreno, Sebastian Trimpe4.00
[abs]Delay-Embedded Representations for Robust Saccade Classification in Noisy Oculographic SignalsVladimir Antipov, Artem Badarin, Alexander Khramov4.00
[abs]BayesAT: Bayes-Guided Progressive Distillation for Semi-Supervised Adversarial TrainingYimo Guo, Lilin Zhang, Li Penglin et al.4.00
[abs]PEEK: One-Step Look-Ahead Exposure Bias Correction for Diffusion SamplingYunwei Bai, Ying Kiat Tan, Tsuhan Chen4.00
[PDF]ViCO: A Training Strategy towards Semantic Aware Dynamic High-ResolutionLong Cui, Weiyun Wang, Jie Shao et al.4.00
[abs]On Nash Equilibria in Participatory Budgeting with Donations and BeyondGRZEGORZ LISOWSKI, Georgios Papasotiropoulos, Grzegorz Pierczyński et al.4.00
[abs]The Multi-Block DC Function Class: Theory, Algorithms, and ApplicationsSayedpouria Fatemi, Hoomaan Maskan, Alp Yurtsever et al.4.00
[abs]WURI: Watching Unfolding Risk in Agent InteractionsYiyang Duan, Tiantong Wu, Yurong Hao et al.4.00
[PDF]AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RLWoosung Kim, Youngjun Suh, Jinho Lee et al.4.00
[abs]ChiP-STAR: Spatial-Topological Attention for Pre-trained Generative Chip RoutingJunfeng Liu, Xingquan Li4.00
[abs]Algorithmic Impact Reveals the Hidden Structure of AlignmentZachary Wojtowicz, Michelle Si, Finale Doshi-Velez et al.4.00
[PDF]TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human FeedbackLei pang, Jun Luo, ruinan Jin4.00
[PDF]FAME: Forecasting Academic Impact via Continuous-Time Manifold EvolutionJianrong Ding, Jianyuan Zhong, Zhengyan Shi et al.4.00
[abs]Decision Focused Scenario Learning for Contextual Stochastic ProgrammingJonathan Hornewall, Tito Homem-De-Mello, Vincent Leclere4.00
[abs]When Are Compositional Problems Learnable from Verifiable Rewards?Daniel Barzilai, Yotam Wolf, Ronen Basri4.00
[PDF]Cascaded Sparse Autoencoders LearnMulti-Level Visual Concepts in Multimodal LLMsYusong Zhao, Hengyi Wang, Tanuja Ganu et al.4.00
[abs]PRISM: Asymmetric Precision-Recall Optimization for Million-Scale Root Cause AnalysisWei Zhang, Rongyao Cai, Xiaosheng Li et al.4.00
[abs]Beyond the Prompt: Leveraging Pre-Decoding States for Jailbreak Detection in dLLMsAdam Hazimeh, Amel Abdelraheem, Ke Wang et al.4.00
[PDF]Incorporating Hierarchical Semantics in Sparse Autoencoder ArchitecturesMark Muchane, Sean M Richardson, Kiho Park et al.4.00
[PDF]Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement LearningSudip Bhujel, Shanghao Shi, Ruiquan Huang et al.4.00
[abs]Complementary Cache Guidance with Gradient Disentanglement for Continuous Test-Time AdaptationFanchun Meng, Yuhang Pei, Jiazhen Huang et al.4.00
[PDF]Online Budget Allocation with Censored Semi-Bandit FeedbackFrançois Bachoc, Nicolò Cesa-Bianchi, Tom Cesari et al.4.00
[PDF]When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol ClassificationWenjie Guan, Jelena Bradic4.00
[abs]When Scores Conflict with Preferences: Calibrated Drift Control for Heterogeneous DPOPing Liu, Yan Yan4.00
[PDF]ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement LearningZuhao Yang, Kaichen Zhang, Sudong Wang et al.4.00
[PDF]Systematic Hazard Sampling: Minimal-Variance Inference for Discrete Diffusion and Flow ModelsSeunghwan Jang, Wonje Jeung, SooJean Han4.00
[abs]Margin Dynamics for Large Language Model AlignmentXingzi Xu, Saygin Seyfioglu, Karim Bouyarmane4.00
[PDF]Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction TuningTao Hu, Da-Wei Zhou4.00
1 If this project is interesting to you, reach out at [email protected].