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
[PDF]Rosetta: Composable Native Multimodal PretrainingXiangyue Liu, Zijian Zhang, Miles Yang et al.4.00
[abs]Anymotion: A Dataset, Benchmark, and Baseline for Controllable Human Motion EditingHaiyang Yan, Jianxin Sun, Yuhan Wu et al.4.00
[abs]Q-Focus: Let the Question Guide What to See in Long VideosJunbo Qiao, Xinning Chai, Dong Fang et al.4.33
[PDF]VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow MatchingTuan D Ngo, Chuang Gan, Evangelos Kalogerakis4.67
[PDF]Generating Symmetric Materials using Latent Flow MatchingAnmar Karmush, Cedric M Brandenburg, Soheil Ershadrad et al.4.00
[abs]DexOPE: 6D Object Pose Estimation in Dexterous ManipulationKe Wu, Zhiwei Yang, Xiangting Meng et al.4.67
[abs]Localizing Concepts in Visual Autoregressive ModelsNanxiang Jiang, Yang Liu, Yuanhao Wang et al.4.33
[PDF]PARE: Pruning and Adaptive Routing for Efficient Video GenerationYutong Wang, Yunke Wang, Tianfan Xue et al.5.00
[PDF]PAI-Actor: Cinematic Multi-Actor Character Replacement in Dynamic ScenesHeyuan Gao, Bangxun Tang, Yiren Song et al.4.00
[PDF]Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image GenerationNaHyeon Park, Minhyun Lee, Hyunjung Shim4.00
[PDF]Temporal Backtracking Search for Test-time Generative Video ReasoningSeJoon Jun, Zheng Ding, Huangyuan Su et al.4.33
[abs]Noise-Regularized Training for Learned Image CompressionRenjie Zou, Zhiwei Huang, Dong Jiang5.00
[PDF]PrismFlow: Residual Dynamics for Flow Matching in Time-Series GenerationJUNRU ZHANG, Lang Feng, Jinbo Wang et al.4.33
[abs]FlowTrack: Controlling Edit-Signal Execution in Inversion-Free Flow Video EditingJielun Zhong, Di Wang, Jisheng Dang et al.4.33
[abs]GEAR: Bridging the Planner-Actor Gap via Gradient-Aligned Policy ExtractionYao-Hui Li, Xin Li, Hasnaa Bennis et al.4.33
[abs]VolCo: Volumetric Contact for High-Fidelity Human Grasp GenerationZhuo Chen, Yihua Cheng, Ales Leonardis et al.4.33
[abs]VUM: Visual Unified Models for Image Generation and PerceptionZiDong Wang, Yiyuan Zhang, Xiaoyu Yue et al.5.00
[PDF]DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation AutoencodersTianhang Wang, Yitong Chen, Wei Song et al.4.33
[abs]AR-Edit: Training-Free Streaming Video Editing without InversionHovhannes Margaryan, Vicky Kalogeiton, Quentin Bammey et al.4.33
[abs]Breaking the Static: Dynamic Text Conditioning for Diverse Image GenerationMeng Yu, Ruidong Chen, qingfeng shi et al.3.67
[abs]MFlowAudio: Efficient Text-to-Audio Synthesis via Mamba-based Stateful Flow MatchingHao Dai, Panyu Chen, Jagmohan Chauhan4.00
[PDF]Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy OptimizationXinwu Ye, He CAO, Li Hao et al.4.33
[abs]Improving Guidance-Free Visual Generation via Self-Contrastive Alignment for Likelihood EstimationJiwan Hur, DongJae Lee, Dongyeun Lee et al.4.33
[abs]Full-Atom Cyclic Peptide Design via Test-Time Scaled Autoregressive Flow MatchingYunpeng Wang, Zhonghui Gu, Runze Ma et al.4.00
[PDF]Generating Physically Consistent Molecules with Energy-Based ModelsChristoph Griesbacher, Lea Bogensperger, Andreas Habring et al.5.00
[abs]She Performs Your Voice: A Unified Speech and Dance Motion ModelLurui Wang, yongkang cheng, Can Xu3.67
[abs]Magnetic Resonance Unpaired Image Translation with Pseudometric Schrödinger BridgesShuwen Wei, Samuel Remedios, Zhangxing Bian et al.3.67
[PDF]Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent ConsistencyShancong (Sean) Mou, Xinhan Yang, Lu Lu4.00
[abs]UniMoE-World: A Unified Mixture-of-Experts Architecture for Scalable Multi-Control Video Generation World ModelingJianjie Fang, Yongyan Xu, Ziyou Wang et al.4.50
[abs]GDMD: Guiding Distribution Matching Distillation with Gradient-Based Reinforcement LearningLinwei Dong, Ruoyu Guo, Ge Bai et al.4.33
[abs]LayoutBridge: Anisotropic Brownian Bridges for Public Indoor Floorplan GenerationTongyang Dai, Ruipeng Gao, Feng Liu et al.4.33
[PDF]Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal DifferencesHanlin Yu, RuiKang OuYang, Partha Kaushik et al.4.33
[PDF]Representation Forcing for Bottleneck-Free Unified Multimodal ModelsYuqing Wang, Zhijie Lin, Ceyuan Yang et al.4.33
[abs]TESLA: Native 4D Gaussian Splatting Generation with Temporally Structured LatentsWeiqi Zhang, Junsheng Zhou, Juntong Fang et al.4.00
[abs]Learning to Deaggregate: Large-scale Trajectory Generation with Spatial PriorsDavid Bergström, Mattias Tiger, Fredrik Heintz4.75
[PDF]Improving Function Space Flow Matching with Kernel Optimal TransportFred Xu, Thomas Markovich, Barbora Barancikova et al.4.33
[abs]ReGen: Agentic Video World Modeling with Synergized Reasoning and GenerationChenguo Lin, Yu Tang, Weiqiao Zheng et al.3.67
[abs]Static-to-Dynamic: Animating Still Mattes via Generative Motion for Video MattingSuqi Song, Jiaqi Xu, Jialuo He et al.4.67
[abs]Decoupling Action from Egocentric Observation for World SimulationYue Ma, Pengjie Song, Xinyu Wang et al.4.25
[abs]iCATS: Fast Video Generation via Interaction-Aware Sparse Attention and Timestep-Adaptive SparsityChengfeng Han, Baole Ai, Xianlu Bian et al.4.00
[PDF]Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video GenerationShengze Wang, Michael Stengel, Tianye Li et al.4.00
[PDF]UniRank: Unified List-wise Reranking via Confidence-Ordered DenoisingPengyue Jia, HailanYang, Shuchang Liu et al.5.00
[abs]SceneShifter: Training-free Multi-Scene Temporal Control for Audio-driven Human AnimationJianzhi Long, Rong-Cheng Tu, Hao Guan et al.3.67
[PDF]ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth ScalingYilang Zhang, Bingcong Li, Niao He et al.4.25
[abs]Measuring and Strengthening Behavioral Suppression in Language ModelsLuxi (Lucy) He, Pengcheng Jiang, Jifan Zhang et al.3.33