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]Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning for T2I Generation in Unified Multimodal ModelsLit Sin Tan, Junzhe Chen, Xiaolong Fu et al.3.67
[abs]Disentangling Optimization Geometry via Hierarchical Polar Adapters for Class-Incremental LearningDat Q Mac, Thanh Hai Dang, Duc-Trong Le et al.3.67
[PDF]Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model IntegritySatchel Grant, Victor Gillioz, Jake Ward et al.3.67
[PDF]StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action ModelsZhe Liu, Jinghua Hou, Yuxiang Lu et al.3.67
[PDF]OptiWorld: Optimal Control for Video World Generation under Physical ConstraintsYu Yuan, Jianhao Yuan, Xijun Wang et al.3.67
[PDF]One More Time: Revisiting Neural Quantum States from a Reinforcement Learning PerspectiveJuan Duque, Sergio García Heredia, Vinicius Hernandes et al.3.67
[abs]Multi-Stage Planning from Single-Stage Data: Reinforcement Learning Helps Composition but Requires AnchoringBoyuan Zheng, Zidong Liu, Yingyu Liang3.67
[PDF]Two is better than one: A Collapse-free Multi-Reward RLIF Training FrameworkShourov Joarder, Diganta Sikdar, Ahsan H Akash et al.3.67
[PDF]Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and TrackingLiying Yang, Hao Mo, Jialun Liu et al.3.67
[PDF]Amortized Molecular Optimization via Group Relative Policy OptimizationMuhammad Bin Javaid, Hasham Hussain, Ashima Khanna-Reiter et al.3.67
[abs]Per-Starting-Point Plausibility and Diversity Bounds for Score-Based Diffusion ModelsMinh Quang Nguyen, Hady Lauw3.67
[PDF]Training-Free Task Vectors for LLM Behavioral ControlGabriel J Perin, Lucas Boscaini, Andre Araujo et al.3.67
[PDF]CausalMix: Data Mixture as Causal Inference for Language Model TrainingZinan Tang, YUKUN ZHANG, Shaomian Zheng et al.3.67
[PDF]The Era of Agentic Organization: Learning to Organize with Language ModelsZewen Chi, Li Dong, Qingxiu Dong et al.3.67
[abs]ORCA: Hunting Compositional Failures in Text-to-Image DiffusionArshia Hemmat, Amirhossein Vahidi, Amitis Shidani et al.3.67
[PDF]Hierarchical Variational Policies for Reward-Guided DiffusionKushagra Pandey, Farrin Marouf Sofian, Jan Niklas Groeneveld et al.3.67
[PDF]Path-independent Flow Matching for Multi-parameter Generative DynamicsFrancisco Téllez, Amirhossein Zamani, Philippe Martin et al.3.67
[PDF]Pooling Versus Ensembling for Ridge Regression Under Covariate ShiftMaya Ramchandran, Rajarshi Mukherjee3.67
[abs]Interactive Combinatorial Reinforcement Learning for Knowledge Graph ReasoningJun Nie, Yonggang Zhang, Tongliang Liu et al.3.67
[abs]A Margin Perspective on LoRA: Robustness to Catastrophic Forgetting and Adapter Merging (MaLoRA)Ziqing Xu, Hancheng Min, Lachlan MacDonald et al.3.67
[abs]Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM AgentsLei Liu, Yunji Liang, Xiaowen Zhang et al.3.67
[PDF]ViT-AdaLA: Adapting Vision Transformers with Linear AttentionYifan Li, Seunghyun Yoon, Viet Lai et al.3.67
[PDF]Enhancing Gaze Reasoning in Vision Foundation Models for Gaze FollowingSHIJING WANG, Yihua Cheng, CHAOQUN CUI et al.3.67
[abs]Cross-Modal Prior-Guided Training with Visual Foundation Models for Unsupervised LiDAR Point Cloud RegistrationKeZheng Xiong, Shiyun Xu, Sheng Ao et al.3.67
[abs]Designing Cell-Type-Specific Regulatory DNA with Guided Discrete DiffusionAnimesh Awasthi, Martin Stoll, Raphael Bednarsky et al.3.67
[abs]Synthetic Web: Benchmarking Language Agents under Adversarial Search RankingShrey Shah, Levent Ozgur3.67
[abs]PriSM: Prior-guided Shared-basis Mixture Personalization for LLMs under Sparse User HistoriesHea Eun Lee, Hyungi Lee, Jangho Kim3.67
[PDF]On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL RegularizationKaixuan Ji, Qiwei Di, Heyang Zhao et al.3.67
[abs]Dual-Pronged LoRA: Achieving Near-Zero Forgetting and High-Performance Adaptation for MLLMsJingqi Ye, haonan he, Minglei Li et al.3.67
[PDF]ReToken: One Token to Improve Vision–Language Models for Visual RetrievalYao Xiao, Reuben Tan, Zhen Zhu et al.3.67
[PDF]Making Open-Source Text LLM Watermarks Durable Against MergingLuisa Scharff, Thibaud Gloaguen, Robin Staab et al.3.67
[PDF]Learning Augmented Exact Exponential AlgorithmsTatiana Belova, Yuriy Dementiev, Danil Sagunov3.67
[abs]SurgReasoner: Surgical Reasoning Segmentation with Dynamic Difficulty-Aware Reinforcement LearningDong Zhang, Cheng Xue3.67
[abs]HARMONY: Hierarchical Anchor Retrieval on Manifold for Oblivious-source Acoustic Anomaly DetectionYuhang Zhang, Yang Li, Mingyuan Li et al.3.67
[abs]I2V-DETACH: Source Grounding Detachment for Unauthorized Image-to-Video GenerationChanhui Lee, Yeonghwan Song, Yewon Kang et al.3.67
[abs]ParaLin: Accelerating Parallel Diffusion Integrator via Intrinsic Partially Linear StructureJianrong Lu, Zhiyu Zhu, Hui LIU et al.3.67
[PDF]Learning POMDP World Models from Observations with Language-Model PriorsValentin Six, Frederik Panse, Mathis Fajeau et al.3.67
[abs]AdaMAP: Learning Adaptive Multi-Action Prediction with Grounded Dreaming GuidanceMuyao Li, Zihao Wang, XuJing Li et al.3.67
[PDF]Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM AgentsZiyan Liu, Zhezheng Hao, Yeqiu Chen et al.3.67
[PDF]VicEdit: Learning to Edit Videos from Visual In-Context ExamplesYuji Wang, Teng Hu, Yuheng Chen et al.3.67
[abs]Reading Positional Coupling in Transformers with Diffusion ScoresSavik Kinger, Johannes Bertram, Luciano Dyballa et al.3.67
[PDF]SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity RegularizationYan Sun, Guoxia Wang, Jinle Zeng et al.3.67
[PDF]Mechanistic Interpretability with Sparse Autoencoder Neural OperatorsBahareh Tolooshams, Ailsa Shen, Animashree Anandkumar3.67
[abs]VisionCreator-S1: Evolving Visual-Generation Agents via Skill-GRPO OptimizationJinxiang Lai, Wenzhe Zhao, HUALEI Zhang et al.3.67
[abs]Calibrated Safe Policy Improvement for Continuous Offline Reinforcement LearningFederico Bianchi, Alessandro Farinelli, Alberto Castellini3.67
[abs]Seeing Together, Acting Apart: Shared Environmental Understanding for Multi-Robot Navigationhaihong hao, Lei Chen, Mingfei Han et al.3.67
1 If this project is interesting to you, reach out at [email protected].