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]HALO-VGGT: Heterogeneity-Aware Lightweight Online Compression Allocator for Efficient VGGTXueling Wang, Yiwen Wang, Siqi Cai et al.4.00
[PDF]Task-Induced Riemannian Metrics for Vision Transformer Feature SpacesAndrew Bond, Ege E Özlü, Tuna Çimen et al.4.00
[abs]Semantic Freedom Bottleneck for Domain-Generalized Multimodal Face Anti-SpoofingYingjie Ma, Haonan Wang, Xun Lin et al.4.00
[abs]RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with LLMsXiao Feng, Bo Han, Zhanke Zhou et al.4.00
[PDF]Spherical Interpolation for Backward-Compatible Multimodal RepresentationsSimone Ricci, Niccolò Biondi, Federico Pernici4.00
[PDF]Working with AI: Measuring the Applicability of Generative AI to OccupationsKiran Tomlinson, Sonia Jaffe, Will Wang et al.4.00
[abs]AIQL: Adaptive Asymmetric Implicit Q Learning for Automated Warehouse ConsolidationGuangyi Liu, Andrea Angiuli, Mirko Ristivojevic et al.4.00
[abs]MOCHA: Discovering Multi-Order Dynamic Causal Structure in Temporal Point ProcessesYunyang Cao, Juekai Lin, Wenhao Li et al.4.00
[PDF]Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache MemoryVatsal Agarwal, Saksham Suri, Matthew Gwilliam et al.4.00
[PDF]Refining Compositional Diffusion for Reliable Long-Horizon PlanningKyowoon Lee, Yunhao Luo, Anh Tong et al.4.00
[PDF]How Much is Left? LLMs Linearly Encode Their Remaining Output LengthMohamed Amine Merzouk, Dmitri Carpov, Mirko Bronzi et al.4.00
[PDF]Motion-o: Trajectory-Grounded Video ReasoningBishoy Galoaa, Shayda Moezzi, Xiangyu Bai et al.4.00
[abs]Foveal-Mamba: Inside-Out Ring Scanning with Recurrent Offset Prediction for Visual State Space ModelsYi-Kuan Hsieh, Jun-Wei Hsieh, Kuan-Chuan Peng et al.4.00
[abs]Wayfinder: Adaptive Resource Routing from Agent CitationsMiguel Romero Calvo, George Karypis4.00
[abs]Causally Structured Differential Network Modeling for Single-Cell Perturbation PredictionJiayi Dong, Xinyue Gu, Fei Wang4.00
[abs]MLLM Makes Strong Backbone for Multi-Modal Object DetectionYifeng Yang, Yutong Li, Jubo Feng et al.4.00
[abs]Brain2voice 2.0: High-performance voice synthesis brain-computer interfaceMaitreyee Wairagkar, Aparna Srinivasan, Nicholas S Card et al.4.00
[abs]gHAWK: Structural Encoding for Scalable Training of Graph Neural Networks on Knowledge GraphsHumera Sabir, Fatima Farooq, Ashraf Aboulnaga4.00
[PDF]Bounding Global and Local Compression Error of Signal ParameterizationsQuang Luong Nhat Nguyen, Sara Fridovich-Keil4.00
[abs]SpecBridge: Learning Natural-Language Formalization Plans for the Formal Specification Synthesis TaskWenjie Zhang, Yun Lin, Zining He et al.4.00
[abs]Matching-while-Decoding: Enhancing Template-Free Retrosynthesis via Explicit Structural AlignmentKaipeng Zeng, Jiarui Shen, Yi Jiang et al.4.00
[abs]NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-TuningJIANHAO ZHANG, Ou Wu, Yi Du4.00
[abs]A Cross-Interaction Neural Architecture for Submodular FunctionsSOUTRIK SARANGI, Aditya Singh, Vansh Maheshwari et al.4.00
[abs]Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free AccelerationShota Takahashi4.00
[PDF]Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action ModelHoeun Lee, Hyeonggeun KIM, Jaeik Kim et al.4.00
[PDF]PACE: A Proxy for Agentic Capability EvaluationYueqi Song, Lintang Sutawika, Jiarui Liu et al.4.00
[PDF]NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual SelectivityYingtian Tang, Sogand Salehi, Ming Zhou et al.4.00
[PDF]Automata from Agent Traces: Failure and Next-Step PredictionSeonglae Cho, Franklin Cardenoso Fernandez, Umar Mohammed et al.4.00
[abs]RECIPE: Learning to Rank Complete Precursor Sets for Inorganic RetrosynthesisJing Gao, Kaipeng Zeng, Fuyuan Xia et al.4.00
[PDF]Local Intrinsic Dimension Unveils Hallucinations in Diffusion ModelsBartlomiej Sobieski, Matthew Tivnan, Dawid Płudowski et al.4.00
[PDF]SpatialClaw: Rethinking Action Interface for Agentic Spatial ReasoningSeokju Cho, Ryo Hachiuma, Abhishek Badki et al.4.00
[abs]VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified TasksTengjv Ru, Weitong Lian, Zecong Tang et al.4.00
[PDF]ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuningDi Zhu, Ziheng Yan, Fang Wan4.00
[PDF]Improving the Efficiency of Language Agent Teams with Adaptive Task GraphsElizabeth Mieczkowski, Alexander Ku, Tiwalayo Eisape et al.4.00
[PDF]Can Large Language Models Develop Gambling Addiction?Seungpil Lee, Donghyeon Shin, Yunjeong Lee et al.4.00
[PDF]LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D GeneratorsXinhe Zhang, Yuyang Zhang, Pengfei Jin et al.4.00
[abs]You CAN Teach an Old Model New Tricks: Domain Adaptation via Complementary Subspace ExpansionDonghoon Han, SungHyun Moon, SeungJae Lee4.00
[PDF]Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image DiffusionSathwik Karnik, Juyeop Kim, Sanmi Koyejo et al.4.00
[abs]Decoupling is the Key: Scaling Deep Value Networks in Reinforcement LeanringYunsheng Xue, Ziyi Zhang, zhihao wu et al.4.00
[PDF]S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHFWei Chen, Guanghui Zhu, Yafei Li et al.4.00
[abs]Universal Adaptive Proximal Gradient Methods via Gradient Mapping AccumulationZimeng Wang, Alp Yurtsever4.00
[abs]CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLAFeiyang Hong, Yujie Wei, Bo Zhao et al.4.00
1 If this project is interesting to you, reach out at [email protected].