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]Rethinking Parallel Multi-Agent Systems: A Cost-Aware Framework for Efficient CoordinationYexiong Lin, Shanshan Ye, Yu Yao et al.4.00
[abs]GeoMemory: Geometry-Indexed Memory for Long-Horizon Interactive Video GenerationJunchao Huang, Xinting Hu, Boyao Han et al.4.00
[PDF]When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-ResolutionYu Shi, Yuyao Zhang, Yu-Wing Tai4.00
[abs]Mitigating Saliency Collapse: Robust Saliency-Aware Long-Text Image-Text AlignmentQiuyu Kong, Zanxi Ruan, Marco Cristani et al.4.00
[abs]Markovian Experimental Design under Concept DriftAyberk Yarkın Yıldız, Lili Su, Carlee Joe-Wong et al.4.00
[abs]Interaction-Aligned Robot Learning from Human Videos with Structured Graph ModelingJiawei Fu, Lin Yang4.00
[PDF]PiCA: Pivot-Based Credit Assignment For Search Agentic Reinforcement LearningDongyi Liu, Yifan Niu, Qinwen Wang et al.4.00
[PDF]GTR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal ModelsJunxian Li, Kai Liu, Zizhong Ding et al.4.00
[abs]Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-ResolutionJinwoo Chung, Jangho Kim4.00
[abs]Track4D: Representing Dense 3D Tracking for Video Diffusion ModelsYushi LAN, Zeren Jiang, Kelvin Zheng Li et al.4.00
[abs]Training Vision Transformers to Focus: Emergence of Attention Head SpecializationYuji Nozawa, Yu-Chieh Lin, Youyang Ng4.00
[abs]AdaAlloc: Adaptive Visual Token Allocation for Long-Video Question AnsweringJoungbin An, Kristen Grauman4.00
[abs]Beyond Uniform Detection: Adaptive Hallucination Detection for RAG Across Response RegimesJungwuk Park, Sejong Ryu, Jy-yong Sohn et al.4.00
[abs]Neuronal Identity as an Organizational Basis for Analyzing Neural Population DynamicsSeungjae Han, Joshua Y You, Soi Kim et al.4.00
[PDF]TED: Text-Axis Evidence Decomposition for Prompted Anomaly LocalizationJINYOUNG KIM, Geonho Kim, GiJeong Park et al.4.00
[PDF]LightMoE: Reducing Mixture-of-Experts Redundancy through Expert ReplacingJiawei Hao, Zhiwei Hao, Jianyuan Guo et al.4.00
[PDF]GMOS: Grounding Moving Object Segmentation in 3D Space and TimeJunyu Xie, Tengda Han, Weidi Xie et al.4.00
[PDF]ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine TranslationKunquan Li, Yingxue Zhang, Zhibin Lan et al.4.00
[abs]Early Detection of Backbone Divergence via Neighborhood Structure in Learned EmbeddingsYiming Zhang, Reza Hassanpour, Georgi Gaydadjiev4.00
[abs]SPECS: Faster Test-Time Scaling through Speculative Drafts and Dynamic SwitchingMert Cemri, Nived Rajaraman, Rishabh Tiwari et al.4.00
[abs]HIST3R: Rectified State Decomposition from History for Streaming 3D ReconstructionKenneth Yang, Frank Wang4.00
[abs]WorldSR: Harnessing World Knowledge Search for Grounded Image Super-ResolutionJunyuan Deng, Xinyi Wu, Zhenyao Wu et al.4.00
[abs]Small Model Portfolios for Many Deployment Profiles: Submodular Coverage under Bundled ConstraintsJi Cheng4.00
[abs]FAVLA: A Force-Adaptive Multi-Rate VLA model for Contact-Rich Robotic ManipulationYao Li, Peiyuan Tang, Wuyang Zhang et al.4.00
[PDF]Toward Multimodal Sheet Music Recognition and UnderstandingGuang Yang, Brian Zheng, Victoria Ebert et al.4.00
[abs]Explanation Mechanism Influences Human Reliance on Reinforcement Learning AgentsXuying Zhong, Daniel Beechey, Crescent Jicol et al.4.00
[PDF]Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM DistillationSeonghoon Yu, Dongjun Nam, Byung-Kwan Lee et al.4.00
[PDF]SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and TopologyYuhao Zhang, Gerard Pons-Moll, Tolga Birdal4.00
[PDF]STRAND: Sequence-Conditioned Transport for Single-Cell PerturbationsBoyang Fu, Sameer Gabbita, George Dasoulas et al.4.00
[abs]CasePlay: Self-Play Reinforcement Learning from Case Reports for Medical ReasoningHao Wang, Zihan Wang, Kai WU et al.4.00
[abs]Koopman Generative Operators for Efficient Probabilistic Time-Series ForecastingRaz Marshanski, Liran Nochumsohn, Mayank Jauhari Iitr et al.4.00
[abs]-Mem: : Efficient Online Memory For Large Language ModelsJingdi Lei, Di Zhang, Junxian Li et al.4.00
[abs]SAPO: Step-Level Skill-Augmented Policy Optimization for Multi-Turn LLM AgentsPrince Z Wang, Shuli Jiang4.00
[PDF]Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented GenerationCan Peng, Yu Liu, Yingyu Yang et al.4.00
[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]Diffusion Masked Pretraining for Dynamic Point CloudZhuoyue Zhang, Yiding Sun, Chaowei Fang et al.4.00
[abs]FreeAct: Demonstration-Free Robot Adaptation via Action-Grounded Generated VideosZhe-Han Mo, Jia-Ning Li, Jiaxi Song et al.4.00
[PDF]Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoringYuxin Wang, Dennis Frauen, Jonas Schweisthal et al.4.00
[PDF]Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video GenerationYanjun Guo, Zhengqiang ZHANG, Pengfei Wang et al.4.00
[abs]Factorized Self-Supervised Speech TokenizationBenjamin Van Niekerk, Jean-Philippe Letendre, Nicol Visser et al.4.00
[abs]CrossID: Cross-Supervised Spatio-Temporal Gated Fusion for Personalized Portrait GenerationDongxu Yue, Qixin Yan, Shiao Yang et al.4.00
[PDF]AnaDiffusion: Anatomically Compositional Latent Diffusion for Controllable 3D Brain MRI GenerationTracy Han, Lulin Liu, Bangya Liu et al.4.00
1 If this project is interesting to you, reach out at [email protected].