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]FedPeel: Peeling Stabilized Layers for Robust Heterogeneous Federated LearningHaizhou Du, Lixin Huang, Zonghan Wu et al.4.33
[PDF]EMO: Pretraining Mixture of Experts for Emergent ModularityRyan Wang, Akshita Bhagia, Sewon Min4.33
[abs]SOAP-Bubbles: Effective and Scalable Variational Learning with Structured CovariancesRobert Adrian Minut, Nico Daheim, Marco Miani et al.4.33
[PDF]Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning RatesThatchanon Anancharoenkij, Donlapark Ponnoprat4.33
[PDF]EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image GenerationSunung Mun, Sunghyun Cho, Jungseul Ok4.33
[PDF]TextSeal: A Localized LLM Watermark for Provenance & Distillation ProtectionTom Sander, Pierre Fernandez, Hongyan Chang et al.4.33
[PDF]Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill ScannersXiaojun Jia, Jie Liao, Simeng Qin et al.4.33
[PDF]Hydra-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor ControlJinhao Zhang, Zhexuan Zhou, Huizhe Li et al.4.33
[PDF]GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose MonitoringZechen Li, Keerthana Natarajan, Weizhi Zhang et al.4.33
[abs]Decomposed Graded Verifier for Generative World ModelingBowei Liu, Xinchen Zhang, Xuhuan Li et al.4.33
[abs]SICAF: Time-Varying Focus Bottleneck for Self-Supervised Event-Based Optical Flow with Spiking Neural NetworkShuangming Yang, Qing He, Shangqi Guo et al.4.33
[abs]HoloCode: A Code-Centric Multi-Agent Framework for Image-to-3D Scene GenerationHanlin Chen, Chung-Ching Lin, Yuyang Zhao et al.4.33
[PDF]Representation Forcing for Bottleneck-Free Unified Multimodal ModelsYuqing Wang, Zhijie Lin, Ceyuan Yang et al.4.33
[abs]GADMVP: Adaptive Few-Shot Graph-Level Anomaly Detection with Multi-View Structured PromptingXiaolin Han, Xiurui Hu, Lingyun Song et al.4.33
[abs]ASAP: Fast Adaptive Sliding Agnostic Poisoning Attack on Federated LearningHUAZI PAN, Yanjun Zhang, Leo Yu Zhang et al.4.33
[abs]Roll2Depth: Zero-Shot Metric Depth Estimation Exploiting Camera's Rolling Shutter EffectRui Xiao, Jinming Xu, Jinsong Han4.33
[PDF]Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMsWanhao Yu, Ziyan Wang, Zheng Wang et al.4.33
[abs]SpikeSTAG: A Dendritic Compartmental Spiking Graph Network for Multivariate Time-Series ForecastingBang Hu, Changze Lv, Junyi Wang et al.4.33
[abs]Co-Evolving Interpolants and Flows via Path-Flow AlignmentZeyu Michael Li, William X Chen, Xiang Cheng4.33
[abs]Readiness-Aware Sample Selection for Noisy Labels with Class ImbalanceChihyeon Choi, Sangho Lee, Jiho Hong et al.4.33
[abs]Balanced Multi-Task Learning from an Optimality-Gap PerspectiveCe Liu, Jianing Huang, HUANG Sicheng et al.4.33
[abs]SPEXT: A Decoupled Multi-Spectral Foundation Model for Earth Observation and Vision-Language GroundingSannara EK, Chong Tang, Dirk Koch et al.4.33
[abs]eSAM: Editing SAM3 Attention for Training-Free Referring SegmentationYaoting Wang, Yun Zhou, Hengrui Hu et al.4.33
[PDF]SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-TuningYongkang Liu, Xing Li, Mengjie Zhao et al.4.33
[abs]SRA: Spatial Reasoning Adapter via Evolving Social Interaction Graphs for Trajectory PredictionJaewoo Jeong, Seonkyu Song, Hyeonwoo Park et al.4.33
[abs]scMAF: Single-Cell Multi-Omics Clustering via Adaptive Modality FusionJun Fu, Yiding Lu, Ruohong Yang et al.4.33
[abs]MODULE: A Mutual-Promoting Deep Unfolding Framework Towards Degradation-Robust Multi-modal Image FusionHan Xu, Yunfei Deng, Jiayi Ma et al.4.33
[PDF]Dual-Pathway Circuits of Object Hallucination in Vision-Language ModelsJiaxin Liu, Ding Zhong, Yue Wang et al.4.33
[PDF]Your Teacher Can’t Help You Here: Combating Supervision Fidelity Decay in On-Policy DistillationYanjiang Liu, Jie Lou, Xinyan Guan et al.4.33
[PDF](Mis)generalization of Helpful-Only Fine-TuningMohammad Omar Khursheed, Baram Sosis, Fabien Roger4.33
[PDF]Bidirectional Sparse Attention for Faster Video Diffusion TrainingChenlu Zhan, Wen Li, Jun Zhang et al.4.33
[abs]Diffusion Meta-Prompting and Steering for Generalizable Foundation Model AdaptationDeepak Sridhar, Yi Li, Kartikeya Bhardwaj et al.4.33
[PDF]POP: Online Structural Pruning Enables Efficient Inference of Large Foundation ModelsYi Chen, Wonjin Shin, Shuhong Liu et al.4.33
[PDF]Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual VideoArslan Artykov, Tom Ravaud, Nicolás Violante et al.4.33
[PDF]VISD: Enhancing Video Reasoning via Structured Self-DistillationHao Lin, Kunyang Lv, Xu Jiang et al.4.33
[abs]PrivateSeal: Low-Sensitivity Latent Directions for Diffusion-Resilient User-Specific WatermarkingYiheng Chen, Zhong Ji, Zhihao Li et al.4.33
[abs]SCG-HF: Semantic Consistency Grouping for Hierarchical Fusion in Video Emotion RecognitionMuci Li, Yujing Rao, He Li et al.4.33
[abs]Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and Large Language ModelsYuan Xie, Jiaqi Song, Xianliang Wang et al.4.33
[PDF]Watermarking Game-Playing Agents in Perfect-Information Extensive-Form GamesJuho Kim, Fei Fang, Tuomas Sandholm4.33
[abs]UGGRH: Unsupervised Generative Completion and Graph-attention Refinement for Incomplete Cross-modal HashingYunfei Chen, Yuchen Zhang, Hongyu Lin et al.4.33
[PDF]SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent LearningHaoqiang Kang, Xiaokang Ye, Yuhan Liu et al.4.33
[abs]Voice "Cloning" Is Actually Style TransferKaitlyn Zhou, Federico Bianchi, Martijn Bartelds et al.4.33
[abs]The Optimization Prior: Instilling depth for shallow networks, detail for coarse networksVighnesh Subramaniam, Boris Katz, Brian Cheung4.33
[abs]SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category SchemaShuang Wu, Jiude Wei, Cewu Lu et al.4.33
[abs]HalluciText: Mitigating Text Hallucinations in Diffusion-Based Image RestorationZhiming Hu, Angela Ye, Ran Zhang et al.4.33
1 If this project is interesting to you, reach out at [email protected].