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]Latent Reasoning in Continuous Space for Unified Multimodal ModelsByungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee et al.4.00
[abs]Source-Causal Control of Historical Context in Longitudinal Radiology Report GenerationDmitry Lvov, Ilya Pershin4.00
[PDF]Heterogeneous Parallelism for Multimodal Large Language Model TrainingYashaswi Karnati, Kamran J Sadeghi, Akash Mehra et al.4.00
[PDF]RePercENT: Scaling Disentangled Representation Learning Beyond Two ModalitiesVasiliki Rizou, Pascal Frossard, Dorina Thanou4.00
[PDF]Test-Time Learning with an Evolving LibraryWeijia Xu, Alessandro Sordoni, Chandan Singh et al.4.00
[abs]Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent QueriesEnpei Zhang, Feiyu Qu, Zheng Huang et al.4.00
[abs]DSBTR: A Diffusion Schrödinger Bridge Trajectory Refiner for Multi-Agent Trajectory PredictionYuxi Xue, Xiangzheng Zhou, Xiaobo Chen et al.4.00
[PDF]Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM AdaptationHaozhan Tang, Xiuqi Zhu, Xinyin Zhang et al.4.00
[abs]From Clips to Streams: A Unified Framework for Streaming Sign Language TranslationHoang Quan Dang, Xin Shen, Yanbin Liu et al.4.00
[PDF]Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual InformationChanho Park, Daehyeon Choi, Jihyun Lee et al.4.00
[abs]Self-Supervised Reconstruction Knockoffs for Calibrated Unsupervised Feature SelectionHaiHui Huang, Dingkui Kang, Yanan Zhou et al.4.00
[PDF]AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline ParallelismThalaiyasingam Ajanthan, Sameera Ramasinghe, Gil Avraham et al.4.00
[abs]Safe Active Learning with Future Viability Guarantees in Time-Series ModelsHyeonjun Park, Whiyoung Jung, Deunsol Yoon et al.4.00
[PDF]VCR: Learning Valid Contextual Representation for Incomplete Wearable SignalsYuxuan Weng, Wenhan Luo, Qijia Shao4.00
[PDF]GeoRouter: Dynamic Paradigm Routing for Worldwide Image GeolocalizationPengyue Jia, Derong Xu, Yingyi Zhang et al.4.00
[PDF]MRNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language ModelingMayank Mishra, Shawn Tan, Ion Stoica et al.4.00
[PDF]Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMsHamed Khosravi, Xiaoming Huo4.00
[PDF]DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation ModelShurui Liu, Weide Chen, Changwang Yi et al.4.00
[abs]Not Suppressing or Purifying: Backdoor Containment via Expert Quarantine and Shutdown in LLMsJianwei Li, Min-Seon Kim, Jung-Eun Kim4.00
[PDF]AVIS: Adaptive Test-Time Scaling for Vision–Language ModelsAhmadreza Jeddi, Minh Le, Amirhossein Kazerouni et al.4.00
[PDF]SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval AgentsMehrdad Saberi, Keivan Rezaei, Soheil Feizi4.00
[PDF]Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive PivotsGuangcheng Zhu, Shenzhi Yang, Haobo Wang et al.4.00
[PDF]Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPOJiahua Yang, Chuangchuang Wang, Zhiwei Yang et al.4.00
[abs]Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided ExplorationSungil Son, Hoseong Jung, Dahyun Oh et al.4.00
[abs]AeroMosaic:Transport-Aware Multimodal Evidence Fusion for Atmospheric Pollution Risk InferenceMuyang Zheng, Jiaming Ma, Zongyu Zhang et al.4.00
[abs]Closing the Loop: Co-Evolving EM for Irregular Time Series Generation in Lifted RepresentationsIdan Arbiv, Gal Fadlon, Omri Azencot4.00
[PDF]Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion ModelsZhiyuan Li, Wenyan Yang, Pekka Marttinen et al.4.00
[PDF]Beyond Pairs: Your Language Model is Secretly Optimizing a Preference GraphNing Liu, Chuanneng Sun, Kristina L Klinkner et al.4.00
[PDF]FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language ModelsFan Mo, Han Yuxuan, Geng Zhang et al.4.00
[abs]Single-Pass Evidence Measurement for Interpretable and Uncertainty-Aware Multimodal Face Anti-SpoofingYingjie Ma, Haonan Wang, Xun Lin et al.4.00
[PDF]Scaling Laws and Tradeoffs in Recurrent Networks of Expressive NeuronsAaron Spieler, Georg Martius, Anna Levina4.00
[PDF]Markovian Dynamics Enforcer: Feasibility Preserving Correction on Learned Dyanmics ManifoldsKevin Yu, Tao Guo, Constantinos Antoniou et al.4.00
[abs]DisSparse: Pipelined Top- Sparse Attention for Long-Context LLM ServingNurlan Nazaraliyev, Elaheh Sadredini, Nael Abu-Ghazaleh4.00
[abs]FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated LearningKonstantinos Ziliaskopoulos, Alexander Vinel, Jiaqi Wang4.00
[PDF]Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual ReasoningYaowu Fan, Tao Han, Dazhao Du et al.4.00
[abs]PGMS: Pyramidal Gaussian Mixture Splatting for 3DGS CompressionXiaoge Zhang, Zijie Wu, Mingtao Feng et al.4.00
[PDF]Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug DesignZaifei Yang, Weiyu Chen, Yaqing Wang et al.4.00
[abs]Characterizing Learning in Deep Neural Networks using a Tractable Algorithmic Complexity EstimatorPedram Bakhtiarifard, Sophia Natasha Wilson, Mahmoud H. A. Afifi et al.4.00
[PDF]VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic ModelJinxiang Lai, Wenzhe Zhao, Zexin Lu et al.4.00
[PDF]SARL: Label-Free Reinforcement Learning by Rewarding Reasoning TopologyYifan Wang, Bolian Li, David Cho et al.4.00
[PDF]CHASM: Cross-frequency Harmonized Axis-Separable Mixing for Spectral Token OperatorsPengcheng Fang, Hongli Chen, Yuxia Chen et al.4.00
[PDF]Attention Sinks and Outliers in Attention ResidualsHaozheng Luo, Haoran Dai, Shaoyang Zhang et al.4.00
[abs]Discovering Programmatic Policies from Reinforcement Learning-Based Traffic Signal ControllersLindong Xie, Yang Zhang, Beiyu Song et al.4.00
[PDF]How deep is your network? Deep vs. shallow learning of transfer operatorsMohammad Tabish, Benedict Leimkuhler, Stefan Klus4.00
[abs]Quantum Best Arm Identification with Limited Round of Adaptivity: Lower Bounds and AlgorithmsHaoran Li, Chen Wang, Xuchuang Wang4.00
[PDF]LinearARD: Linear-Memory Attention Distillation for RoPE RestorationNing Yang, Hengyu Zhong, Wentao Wang et al.4.00
1 If this project is interesting to you, reach out at [email protected].