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]Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAsJiahui Niu, Kefan Gu, Yucheng Zhao et al.4.00
[abs]CHoRD: Coordinating Scheduling and Data Placement for Efficient Deep Neural Network Inference on Chiplet-Based GPUsHanpei Liu, Samit S Miftah, Dipali Jain et al.4.00
[PDF]TimeClaw: A Time-Series AI Agent with Exploratory Execution LearningHangchen Liu, Dongyuan Li, Renhe Jiang et al.4.00
[PDF]Inertia-1: An Open Exploration of Wearable Motion Foundation ModelsZongzhe Xu, Aakarsh Anand, Sarah Jiang et al.4.00
[abs]Reranking with Intra-modal Visual Association for Text-to-Image Person Re-IdentificationJunhong Wang, Changxing Ding, Yusha Peng et al.4.00
[PDF]Fine-tuning language encoding models on slow fMRI improves prediction for fast ECoGAditya Vaidya, Richard Antonello, Alexander Huth4.00
[abs]FlashRelight: Portrait Video Relighting with Dynamic LightingJiahui Sheng, Le Li, Limin Lin et al.4.00
[abs]MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual AugmentationZhihan Yin, Jianxin Liang, Yifeng Yao et al.4.00
[abs]Taking Low-Rank LLM Compression a Step Further: A Global Perspective with Fused InferenceXinhao Huang, Yuqiang He, Zeyi Wen4.00
[PDF]ReFree-S2V: Towards Realistic Co-Speech Video Generation via Reward-Free RL and Multilevel Speech GuidanceSalaheldin Mohamed, M. Hamza Mughal, Rishabh Dabral et al.4.00
[PDF]PixelDense: Dense Prediction as Representation Alignment for Pixel DiffusionLehan Yang, Daiqing Qi, Wenhao Zhang et al.4.00
[PDF]PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action RecognitionSanghyeon Lee, Jinwoo Kim, Jong Taek Lee4.00
[abs]POISE: Instance-Specific Prompt Tuning under Latent Mixture Target Distributionswenhao zheng, shuai xu, Lixing Chen et al.4.00
[abs]CC-GS: Low-Memory 3D Gaussian Splatting Training via CPU-GPU Block-Wise Context CompositingJian Xu, Siyi Wu, Yi Li et al.4.00
[PDF]Tool-IQA: Augmenting Image Quality Assessment with Simple ToolsGuanyi Qin, Junjie Zhang, Chunming He et al.4.00
[abs]Beyond Distribution Matching: Self-Supervised Representation Forcing for Few-Step Video GenerationJunyi Chen, Haiyu Zhang, ZHOUJIE FU et al.4.00
[abs]SteerCast: Retrieval-Based Latent Steering for Decoder-Only Time Series ForecastingVan Dai Do, Huu H Nguyen, Minh Hoang Nguyen et al.4.00
[PDF]Reflection with Action-Induced Visual Differences for Desktop GUI AgentsYijie Ma, Chaoyue Niu, Fan Wu et al.4.00
[abs]Spatially-Grounded Long Video Generation with Self Geometry ForcingChenguo Lin, Panwang Pan, Bowen Xue et al.4.00
[abs]IMTS-Tokenizer: Time-Aware Tokenization for Irregular Multivariate Time Series ForecastingBin Xu, Yinghua Li, Linqi Han et al.4.00
[abs]From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent CommerceXianyang Liu, Shangding Gu, Fan Xu et al.4.00
[abs]PhyMo: Learning Physical Dynamics with Accurate and Continuous Motion from Multi-View VideosShangjia Liu, Jinxi Li, Siyuan Zhou et al.4.00
[abs]PACO: Partial-order-Augmented Continuous Optimization for Differentiable Causal DiscoveryXiaoxuan Li, Junda Wu, Julian McAuley et al.4.00
[abs]Making LoRA Identifiable: Orthogonal Alignment for Continual LearningPratik Rakesh Singh, Mohammadi Zaki, Akash Saha et al.4.00
[abs]AmbiguousWorld: Benchmarking and Resolving Ambiguous Instructions in Video World ModelsBo Wang, Sen Cui, Jin Li et al.4.00
[PDF]TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D TrackingJisu Nam, Jahyeok Koo, Soowon Son et al.4.00
[abs]Scalable Fair Learning via Cramér-von Mises RegularizationAlbert Gimó Contreras, Mariia Vladimirova, Olga Petrova et al.4.00
[abs]WorldVLA: A Unified Vision-Language-Action and World ModelJun CEN, Siteng Huang, Yuqian Yuan et al.4.00
[PDF]PAMod: Modeling Cyclical Shifts via Phase-Amplitude Modulation for Non-stationary Time Series ForecastingYingbo Zhou, Yutong Ye, Shuhao Li et al.4.00
[abs]Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous DrivingXingtai Gui, Yucheng Zhou, Dongqian Guo et al.4.00
[abs]BioMicroAgents: A Co-evolutionary Multi-Agent Framework for High-Fidelity Biomicroscopy ImagingYongwei Jiang, Peilin Li, anfu deng et al.4.00
[PDF]UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative DecodingYepeng Weng, Qiao Hu, Takehisa Yairi4.00
[abs]ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich ManipulationPeiyuan Tang, Yao Li, Xiaodong Zhang et al.4.00
[abs]Newton-PINet: A fast physics-informed neural network with Newton linearization for meta-learning nonlinear PDEsYuchen Fan, Chang Wei, Pao-Hsiung Chiu et al.4.00
[abs]Hawkeye: Hardware-Aware GPU Kernel Optimization with Minimal SupervisionArya Tschand, Kesavan Ramakrishnan, Alexander Ingare et al.4.00
[abs]-VLA: Automatic Perception-Guided Attention Alignment for Robot ManipulationShengzhe Zhang, Qi Zhang, Dazhong Shen et al.4.00
[PDF]From “Weak” Signals to Strong Models: Preference Delta Aggregation with LoRA MergingQi Sun, Siyue Zhang, Yulin Chen et al.4.00
[abs]One Adapter For All: Towards Generalizable Many-To-One Domain Adaptation In Heterogeneous Collaborative PerceptionLu Bin, Zhewei Fu, Shaohong Wang et al.4.00
[abs]Fully First-Order Algorithms for Online Non-Convex Bilevel OptimizationTingkai Jia, Ting Wang, Cheng Chen4.00
[PDF]FreeSpec: Training-Free Long Video Generation via Singular-Spectrum ReconstructionFangda Chen, Shanshan Zhao, Longrong Yang et al.4.00
[PDF]VLMs Trace Without Tracking: Diagnosing Failures in Visual Path FollowingHyesoo Hong, Min S Kim, Wonje Jeung et al.4.00
[abs]HandXFM: Semantic-Structural Distillation for Hand Radiograph Foundation ModelsYuxi Long, Ganlin Feng, Lianghong Chen et al.4.00
[PDF]Agentic Abstention: Do Agents Know When to Stop Instead of Act?Han Luo, Bingbing Wen, Lucy Lu Wang4.00
[abs]VICO: Visual Environments Co-Evolving for Vision-Language Model ReasoningMeng Lu, Ligeng Zhu, Olivia Xiao et al.4.00
[PDF]Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road UnderstandingLena Wild, Katie Luo, Marco Pavone4.00
1 If this project is interesting to you, reach out at [email protected].