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.
[PDF]MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent MemoryZhenyuan Zhang, Jia Xianzhang, Zhiqin Yang et al.3.40
[abs]Uncertainty Aware SURE Transfer Learning for Classification ProblemsHaoyue Li, Shubo Li, Runze Li3.40
[PDF]Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMsMing-Hao Hsu, Yuxuan Hu, Shujie LIU et al.3.33
[abs]Unifying Partner and Environment Diversity to Improve Human-AI CoordinationPatrick Q Zhang, Yancheng Liang, Adrienne Fairhall et al.3.33
[PDF]HOPE: Hand-Object Pressure Estimation from Monocular VideosSubin Jeon, Byungjun Kim, Hanbyul Joo3.33
[PDF]Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial AnimationHyung Kyu Kim, Byungchan Hwang, HAKGU KIM3.33
[PDF]Training with Harnesses: On-Policy Harness Self-Distillation for Complex ReasoningZhengyang Zhao, Lu Ma, Wentao Zhang3.33
[PDF]Progressive Risk Estimation for Accident AnticipationSamet Hicsonmez, Eray Çakar, Nermin Samet et al.3.33
[PDF]Motion Cues from Image-based Point Tracking for LiDAR Scene Flow EstimationYoungdong Jang, Gyeongrok Oh, Jong Wook Kim et al.3.33
[abs]Adaptive Multi-Frame Learning for Expressive and Stable Atomic RepresentationsJun Wang, Yifan Zeng, Bo Han et al.3.33
[PDF]DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion ConvergenceXu Huang, Ye Huang, Zijun Liao et al.3.33
[PDF]Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptationzhiqi yu, Zhangquan Chen, Mengting Liu et al.3.33
[abs]IDEAL: Interaction Dynamics and Force-Aware Learning for Dual-Humanoid Collaborative ManipulationZhaoyang Li, Chiyu Zhang, Chaoyue Li et al.3.33
[abs]MSR-3D: Multi-Mode Semantic Representation for Open-Vocabulary 3D Scene UnderstandingJianan Fu, ting Wu, Rui Yang et al.3.33
[abs]Achieve Latency-Efficient Temporal-Coding Spiking LLMs via Discretization-Aware ConversionJinjie Fang, Tianxing Man, Xiao Du et al.3.33
[abs]EgoMo3R: Joint Egocentric Motion and Scene ReconstructionChaitanya Patel, Yusuke Kato, Rin Takahira et al.3.33
[abs]Nüwa.RNA: An RNA Foundation Model for Unified Representation with Deep Structure InfusionKun Huang, Jiyang Li, Xin Guo et al.3.33
[PDF]Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMsAmr Abourayya, Jens Kleesiek, Michael Kamp3.33
[abs]Scalable Neural Safety Certification via MonotonicityAmirreza Alavi, Majid Zamani, Saber Jafarpour3.33
[abs]AsymPipe: Accelerating Large-scale DiTs Image Editing via Asymmetry-Aware Pipeline ParallelismHuage Deng, LYU WENKAI, WU YONGJIN et al.3.33
[abs]Mitigating Knowledge Conflicts in Retrieval-Augmented Generation via Inference-Time Representation EditingDahyun Jung, Jaehyung Seo, Heuiseok Lim3.33
[abs]Recovering Evolving User Preference State via Adaptive Interaction-aware Representation CorrectionParthiv Chatterjee, Dhiraj Golhar, Ummesalma Diwan et al.3.33
[PDF]Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual SteeringGerasimos Chatzoudis, Zhuowei Li, Gemma Moran et al.3.33
[abs]EVA: Evidence-seeking Visual Agent for Hallucination-Resistant Multimodal ReasoningTing Lei, Yu Chen, Yang Liu3.33
[PDF]SpatialFlow-GRPO: Where Spatial Credit Drives Image EditingYankai Yang, Yancheng Long, Wei Chen et al.3.33
[abs]Cheap Talk, Real Stakes: Commitment and Exploitation in Human-LLM Strategic InteractionArtyom Kabanov, Mikhail Mozikov, Sergei Volchkov et al.3.33
[abs]Geometry is an Operator: Lie-Algebraic Space Routing for View-Robust 3D MLLMsJingjun Yi, Chen Hu, Qi Bi et al.3.33
[abs]Eliciting Zero-Shot Named Entity Recognition in Large Language Models via Instruction Semantic ElaborationKaiyin Zhou, zhiyi Song, Xiangling Fu et al.3.33
[abs]Memory-Efficient Federated Fine-Tuning of LLMs via Block-wise Progressive TrainingQianyue Cao, Zongwei Zhu, Boyu Li et al.3.33
[abs]Progressive Layer-wise Supervision: Deep-to-Shallow Supervision Annealing for Efficient and Robust Speech Deepfake DetectionHoan My Tran, Xin Wang, Xuechen Liu3.33
[abs]A Unified Framework for Image-to-3D Part Generation via Variable GranularityQiwen Gu, Xin Zhou, Xiwu Chen et al.3.33
[PDF]BALTO: Balanced Token-Level Policy Optimization for Hallucination MitigationNing Li, Zixuan Guo, Yan Xu et al.3.33
[abs]Language Denoising Objectives Extend the Value of Limited DataJustin Lovelace, Christian Belardi, Srivatsa R Kundurthy et al.3.33
[abs]Phase-wise Velocity Distillation: Towards Effective Image Generation with A Single NFEZhen Guo, Rongyuan Wu, Qiaosi Yi et al.3.33
[PDF]Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction–Concealment Tradeoff in MLLMsMd Farhamdur Reza, Richeng Jin, Tianfu Wu et al.3.33
[PDF]MIND: Monge Inception Distance for Generative Models EvaluationQuentin Berthet, Clement CREPY, Romuald Elie et al.3.33
[PDF]Event-Grounded Sparse Autoencoders for Vision-Language-Action PoliciesXinchen Jin, Aditya Chatterjee, Pranav Kumar et al.3.33
[abs]QueryStop: Dynamic Stop Signals for Efficient Streaming InferenceMichelle Shu, Jingyao Li, Pengguang Chen et al.3.33
[abs]Reinforced Evidence-Aware Long Video UnderstandingYuan Xie, Tianshui Chen, Deyu Zhou et al.3.33
[abs]Pareto DNN Verification: Fast for Most QueriesYizhak Y. Elboher, Avraham Raviv, Amihay Elboher et al.3.33
[abs]From Generation to Restoration: Residual Diffusion for Neural Channel DecodingQinshan Zhang, Shipeng Guo, Xuantai Wu et al.3.33
[abs]Why DiT Models Underperform as Representation Learners without Long Skip ConnectionsBenyuan Meng, Yiliang Zhang, Jin-Wen Wu et al.3.33
[abs]Beyond Flat Walks: Compositional Abstraction for Autoregressive Graph GenerationKaiwen Bian, Andrew H Yang, Ali Parviz et al.3.33
[abs]Learnable Diffusion-based Positional Encodings for Link PredictionJiaji Ma, Murad Huseynli, Danai Koutra3.33
[abs]An Efficient Cross-modal Feature Reconstruction Model for Multimodal Multi-class Anomaly DetectionZhenghan Wang, Zhihui Luo, Haitao Hu et al.3.33
[PDF]See it to Place it: Evolving Macro Placements with Vision Language ModelsIkechukwu Uchendu, Swati Goel, Karly Hou et al.3.33
[abs]Planning Persuasion, Not Utterances: Profile-Conditioned Open-Loop Search for Dialogue StrategyZhiming Lin, Kai Zhao, Yuliang Gai et al.3.33
[PDF]Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable RewardsShuze D Liu, Claire Chen, Jiabao S Xiao et al.3.33
1 If this project is interesting to you, reach out at [email protected].