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]Tune-Up Open-Weight CLIP: Optimization Framework for Self-Supervised Fine-tuning of CLIPAnant Mehta, Xiyuan Wei, Xingyu Chen et al.4.67
[PDF]Extracting Search Trees from LLM Reasoning Traces Reveals Myopic PlanningSixing Chen, Ji-An Li, Saner Cakir et al.4.67
[PDF]Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series ForecastingXingyu Zhang, Jingyao Wang, Xin Yu et al.4.67
[abs]StructBridge: Structure-Grounded 3D Indoor Object Generation via 3D Latent Diffusion Bridge and Normal RefinementNange Wang, Zhanxu Bai, Yuxuan Li et al.4.67
[PDF]CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative ModelsChengqian Zhang, Yucheng Jin, Duo Zhang et al.4.67
[abs]Enhancing LLMs with Cognitive-Affective Personality Inference for Simulating Human Social-Psychological BehaviorZhibo Deng, Dongyuan Li, Shuwen Ge et al.4.67
[abs]Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-TuningJintao Zhang, Kai Jiang, Chendong Xiang et al.4.67
[abs]EditDistill: Is It Possible to Guide Video Editing with Image Editingguojun lei, Hong Li, Hongbing Yang et al.4.67
[PDF]Stable Long-Horizon PDE Forecasting via Latent Structured Spectral PropagatorsXiaoxiao Lu, Ye Yuan, Jiahao Shi4.67
[abs]UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via PropagationBangwei Guo, Yunhe Gao, Meng Ye et al.4.67
[PDF]Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs InferenceQuantong Qiu, Zhiyi Hong, Yi Yang et al.4.67
[abs]Resolution-Aware Structural Density Peak ClusteringJie Yang, Hsiang-Ting Chen, Yan Ma et al.4.67
[PDF]Horizon Adaptive Offline Policy Learning via Value StitchingKexin ZHENG, Xianyuan Zhan, Xintao Yan4.67
[PDF]ECHO: Terminal Agents Learn World Models for FreeVaishnavi Shrivastava, Ahmed Awadallah, Dimitris Papailiopoulos4.67
[abs]Basis-Mediated Bilinear Attention: A New Method for Greatly Reducing Query–Key Pathway ParametersWei Chen, Wenhao Jiang, Yiying Yang4.67
[abs]LLM-Enhanced Random Forests in Orthogonal Hyperbolic Subspaces for Tabular LearningShengpeng Wang, Yisen Gao, Han Xiang et al.4.67
[PDF]TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary SpectraWeiwei Ye, Renhe Jiang, Hangchen Liu et al.4.67
[PDF]EditBridge: Towards Faithful and Efficient Ultra-High-Resolution Image EditingJiayi Song, Shijie Huang, Fangtai Wu et al.4.67
[PDF]Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-TrainingYuanyi Wang, Yifan Yang, Su Lu et al.4.67
[PDF]EmpathyChat: Structured Cognitive Reasoning in Empathetic Spoken DialogueDingdong WANG, Shujie LIU, Jinyu Li et al.4.67
[abs]PoSafeNet: Structured Safety Learning via Compositional ProjectionKiwan Wong, Wei Xiao, Daniela Rus4.67
[PDF]It's All Training: A Fully Synthetic Single-Stage Recipe for LLMsPierre-Carl Langlais, Pieter Delobelle, Yannick Detrois et al.4.67
[abs]RelGS: Relation-Aware Gaussian Splatting for Open-Vocabulary 3D Scene UnderstandingKai Zhao, Dai Shi, YIXIN CHEN et al.4.67
[abs]DiagSQL: A Diagnostic Validator for Text-to-SQL with Reward Allocation and Co-occurrence ShapingWeibin Liao, Bowen Cao, Dong Fang et al.4.67
[abs]Task-Aware KV Cache Compression for LLM Agents via Utility-Driven Step PruningYusen Wu, Yefan Wang, Jia Yee Tan et al.4.67
[abs]On the Effect of Token Correlations on Semantic Transfer in TransformersNevena Lazic, Julian Zimmert, Alan Malek et al.4.67
[PDF]The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of AbstainingGavin Vy Nguyen, Ziqi Xu, Jeffrey Chan et al.4.67
[PDF]Beyond Steering Vector: Flow-based Activation Steering for Inference-Time InterventionZehao Jin, Ruixuan Deng, Junran Wang et al.4.67
[abs]CASQRec: Collaborative-Adaptive Semantic Quantization for Multimodal RecommendationQingfeng Li, Wenhui Tu, Wei Liu et al.4.67
[PDF]Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow MatchingQianxin Xia, JIAWEI DU, Yuhan Zhang et al.4.67
[PDF]Learning-Augmented Online Scheduling with Parsimonious PreemptionMugen Blue, Sungjin Im, Alexander Lindermayr4.67
[PDF]DiRecT: Safe Diffusion-Based Planning via Receding-Horizon DenoisingPaolo Giaretta, Zeyang Li, Navid Azizan4.67
[PDF]RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPOYanzuo Lu, Ronglai Zuo, Jiankang Deng4.67
[PDF]CoreQ: Learning-Free Mismatch Correction and Successive Rounding for QuantizationSeohyeon Cha, Huancheng Chen, Dongjun Kim et al.4.67
[PDF]No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View VideosMatteo Balice, Yanik Künzi, Chenyangguang Zhang et al.4.67
[PDF]The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from HumansOdysseas S Chlapanis, Orfeas Menis Mastromichalakis, Christos H Papadimitriou4.67
[PDF]End-to-End Training for Unified Tokenization and Latent DenoisingShivam Duggal, Xingjian Bai, Zongze Wu et al.4.67
[abs]Complexity Aware Continuous Level of Details for Gaussian SplattingRadu Beche, Raoul de Charette4.67
[abs]Where and When Identity Forms: Identity-Vital Attention Redistribution for Training-Free Subject-Driven GenerationLuan Thanh Trinh, Atsuki Osanai, Kenji Doi4.67
[PDF]The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM ReproducibilityDavid Pape, Jonathan Evertz, Lea Schönherr4.67
[abs]FiedlerPrune: Connectivity-Preserving Cross-Layer Pruning for Large Language ModelsZijun Sun, Yanning Shen4.67
[abs]3R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction ModelZixiang Ai, Zhenyu Cui, Xu Zou et al.4.67
[abs]NeuroFaith: Evaluating Mechanistic Faithfulness of LLM Free Text Self-Explanation at the Concept LevelMilan Bhan, Jean-Noël Vittaut, Nicolas CHESNEAU et al.4.67
[PDF]Scalable Derivative Gaussian Processes via Exact Gradient ReductionHyunseok Seung, Matthias Katzfuss4.67
1 If this project is interesting to you, reach out at [email protected].