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
[abs]Diffusion Fine-Tuning: Iterative Refinement for Advanced Grounding with Diffusion Large Language ModelsZhangyang Qi, Jinsong Li, Jiaqi Wang et al.4.25
[PDF]Principled Design of Diffusion-based Optimizers for Inverse ProblemsJulio Oscanoa, Irmak Sivgin, Cagan Alkan et al.4.33
[PDF]Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space ViewYixian Xu, Yuanrui Zhang, Shengjie Luo et al.4.33
[PDF]Test-Time Scaling with Diffusion Language Models via Reward-Guided StitchingRoy Miles, Aysim Toker, Andreea-Maria Oncescu et al.4.33
[abs]WORD: Diffusion-Based Posterior Inference for Online Goal RecognitionAlmog Anschel, Sarah Keren4.33
[abs]Skill-Adaptive Noise Scheduling for Diffusion PoliciesWoo Kyung Kim, Gwangpyo Yoo, Eunyoung Park et al.4.33
[abs]Improving the Diffusability of Motion TokenizerGuanhe Huang, Songqiao Han, Tangzheng Lian et al.4.67
[PDF]Exploring MLLM-Diffusion Information Transfer with MetaCanvasHan Lin, Xichen Pan, Ziqi Huang et al.4.67
[abs]DNS-Calibrated Local Stochastic Transition Closure for PDE-Free Long-Horizon Turbulence DiffusionZhuoer Lin, Wenwu He, Congcong Liu et al.4.33
[PDF]Continual Learning in Modern Hopfield Networks with an Application to Diffusion ModelsKen Takeda, Masafumi Oizumi, Ryo Karakida4.00
[PDF]Oversmoothing as Representation Degeneracy in Neural Sheaf DiffusionArif Dönmez, Ellen Fritsche, Axel Mosig et al.3.67
[PDF]Hydra-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor ControlJinhao Zhang, Zhexuan Zhou, Huizhe Li et al.4.33
[PDF]An exact information theory of generalization phase transitions in Bayesian diffusion modelsHenry Hunt, Mason Kamb, Surya Ganguli4.67
[PDF]Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM AgentsKaixuan Liu, GUOJUN XIONG, Weinan Zhang et al.4.33
[PDF]Cyclic Denoising Reveals Ultrastable Memories in Diffusion ModelsRishabh Sharma, Stefano Martiniani4.00
[abs]What Kind of Diffusion Models Do We Need in Online Reinforcement Learning?Zihao Wu, Hongyao Tang, Yi Ma et al.4.33
[abs]Zero-Shot Burst Restoration via Diffusion MAP Inference with Poisson-Gaussian Noise LikelihoodZiyao Yi, Luca Savant Aira, Diego Valsesia et al.4.00
[PDF]PixelDiT2: Representation-Grounded Pixel Diffusion TransformersYongsheng Yu, Wei Xiong, Yichen Sheng et al.5.00
[PDF]ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory ModelingBrian Nlong Zhao, Ozgur Kara, Junho Kim et al.4.00
[abs]StyleRoute: Diffusion Style Transfer via Regional Routing and Conflict-aware ProjectionXunhao Lin, Yu Sun, Xinpeng Ding et al.3.67
[PDF]Constrained Code Generation with Discrete DiffusionLize Shao, Michael Cardei, Zichen Xie et al.4.67
[abs]Continuously-Augmented Hybrid Masked Diffusion Model for Data ImputationKijung Jeon, Molei Tao4.00
[PDF]DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series ForecastingWeiwei Ye, Dongyuan Li, Hangchen Liu et al.4.67
[PDF]Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion ModelsRoi Benita, Miki Elad, Joseph Keshet3.75
[abs]MiCo: Microstructure-Consistent Flow Matching for Diffusion MRI Angular Super-ResolutionZhixuan Zhou, Tingting Dan, Guorong Wu4.67
[abs]Focus, Align, and Diffuse: Time-Series-Aware Keyframe Diffusion for Cardiac Dynamic Synthesis from Sparse ObservationsJunkai Liu, Haofan Wu, Nay Aung et al.4.67
[PDF]GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion TrajectoriesArpita Joshi4.00
[PDF]MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLMOmin Kwon, Yeonjae Kim, Doyeon Kim et al.4.33
[abs]Mixed-Curvature Geometric Latent Diffusion Model for Graph GenerationMinxue Qi, Xian Yang, Liang Bai4.25
[PDF]Discretizing Continuous Time Series for Imputation with Masked Diffusion TrainingDongbin Kim, Seungyun Lee, Geonwoo Shin et al.5.00
[abs]Trajectory-Consistent Diffusion Policies for Offline Reinforcement LearningYichao Fu, Shangde Gao, Zhuoling Li et al.4.33
[PDF]CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion ModelsZhenghao He, Guangzhi Xiong, Boyang Wang et al.4.33
[PDF]HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series ImputationHongfan Gao, Wangmeng Shen, Bin Yang et al.4.00
[PDF]LangFlow: Continuous Diffusion Rivals Discrete in Language ModelingYuxin Chen, Chumeng Liang, Hangke Sui et al.4.33
[abs]FrequencyBooster: Advancing Pixel Diffusion for High-Fidelity Image GenerationLichen Ma, Zipeng Guo, Yu He et al.3.67
[PDF]Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular DiffusionEugenio Lomurno, Filippo Balzarini, Francesco Benelle et al.4.00
[abs]Unsupervised Concept Discovery with Dirichlet Concept Diffusion ModelsYuchong Geng, Ao Tang3.00
[abs]EGCA: A Spectral Perspective on Forward Process Design in Diffusion ModelsChi Zhang, Guichao Chang, Sirui Liu et al.4.00
[PDF]Ultra Fast PDE Solving via Physics Guided Few-step DiffusionXiangrui Cindy Kong, Yueqi Wang, Haoyang Zheng et al.4.00
[PDF]Diffusion Path Samplers via Sequential Monte CarloJames Matthew Young, Paula Cordero-Encinar, Sebastian Reich et al.4.67
[PDF]DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion ConvergenceXu Huang, Ye Huang, Zijun Liao et al.3.33
[PDF]MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion ModelsHojung Jung, Rodrigo Hormazabal, Jaehyeong Jo et al.4.00
[PDF]Statistical Convergence of Spherical First Hitting Diffusion ModelsSimon Bienewald, Lukas Trottner4.33
[PDF]Spectral Feedback for Test-Time Alignment of Protein Diffusion ModelsShai Dickman, Mert Cemri, Landon Butler et al.3.67
[abs]A Favorable Regime Between ODE and SDE for Few-Step Diffusion SamplingYIhao Bu, Dan Lian, Zhenguo Gao4.75