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]PCBSchemaGen: Reward-Guided LLM Code Synthesis for Printed Circuit Boards (PCB) Schematic Design with Structured VerificationHuanghaohe Zou, Peng Han, Emad Nazerian et al.4.00
[PDF]Masked Diffusion Vision-Language Models for Temporal Action LocalizationFengshun Wang, Zhengbo Zhang, Zhigang Tu4.00
[PDF]Agentic Multi-Turn Reasoning: A Fairness ApproachThanh-Dat Truong, Sankalp Pandey, Hugh Churchill et al.4.00
[abs]Distributionally Robust Algorithmic Recourse for Tree EnsemblesKentaro Kanamori, Ken Kobayashi, Takuya Takagi4.00
[abs]Orthogonal Origin Parking: Decoupling Lorentz Manifolds for Robust OOD GeneralizationPeter J Kampen, Anders N Christensen, Morten Rieger Hannemose et al.4.00
[PDF]Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label NoiseKumar Shubham, Pavan Karjol, Kiran M K et al.4.00
[abs]FlowLeak: Coverage-Guided Extraction of Dynamic Workflows in LLM-Based Multi-Agent SystemsZhiyao Ren, Siyuan Liang, Yibing Zhan et al.4.00
[abs]Mitigating Compounding Errors in Online Reinforcement Learning via Optimal Transport Regularized Flow MatchingBoxiang Tao, Lei Guo, Bin Wang et al.4.00
[abs]Denoising-Time Heterogeneity in VLA Action Generation: A Controlled Study via Step-Wise ExpertBaolong Gao, Yuhan Dong, Xudong Zhang et al.4.00
[PDF]One for All: A Non-Linear Transformer can enable Cross-Domain Generalization for In-Context Reinforcement LearningBowen He, Juncheng Dong, Lin Lin et al.4.00
[PDF]Confidence-Based Decoding is Provably Efficient for Diffusion Language ModelsChangxiao Cai, Gen Li4.00
[PDF]Improving constraint-based discovery with robust propagation and LLM priorsRuiqi Lyu, Alistair Turcan, Martin J Zhang et al.4.00
[abs]SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed MaskingMoonseok Choi, Giung Nam, Jongwon Jeong et al.4.00
[PDF]SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and HybridityZhenghao Gan, Yichen Bao, Yifei Liu et al.4.00
[abs]On the Origin of Algorithmic Progress in AI: Evidence from Language Model Pre-TrainingHans Gundlach, Alex Fogelson, Jayson Lynch et al.4.00
[PDF]SALT: When More Rollouts Don’t Help in Group-Based Policy Optimization and How to Make Them MatterPowei Chang, Jinpeng Zhang, Chaoqun Sun et al.4.00
[abs]Posterior Alternative Calibration in Ambiguous Inverse ProblemsJing Qiao, Yiyang Guo, Hao Ye4.00
[PDF]What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow MatchingAlec Helbling, Sebastian Gutierrez Hernandez, Benjamin Hoover et al.4.00
[abs]A probabilistic model of visual segmentation explains early visual cortical dynamicsTridib K. Biswas, Ruben Coen-Cagli4.00
[abs]Ballad: Bandit-Based LLM Routing for Automated Heuristic DiscoverySamidha Verma, Ankit Anand, Sayan Ranu4.00
[PDF]Pure Exploration Beyond Reward Feedback: The Role of Post-Action ContextMohammad Shahverdikondori, Amir Mohammad Abouei, Alireza Rezaeimoghadam et al.4.00
[abs]Angular Networks: Low-Bit Learning from Randomized Similarity EstimatorsAli Ahmed, Saeid Pourmand, Muhammad Awais et al.4.00
[PDF]VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample EditingKijung Jeon, Thuy-Duong Vuong, Molei Tao4.00
[PDF]EfficientRollout: System-Aware Self-Speculative Decoding for RL RolloutsMinseo Kim, Minjae Lee, Seunghyuk Oh et al.4.00
[abs]The Path Not Taken: RLVR Learns Off the PrincipalsHanqing Zhu, Zhenyu Zhang, Hanxian Huang et al.4.00
[PDF]Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive AlgorithmsNathan White, Krish Singal4.00
[abs]Diffusion-Enhanced GFlowNet for Solving Vehicle Routing ProblemsNi Zhang, Zhiqin Zhang, Ling Pan et al.4.00
[PDF]On the Design Space of Discrete Diffusion Online Adaptation for Molecular OptimizationTrevor Chen, Ariel Dai, Jason Yang et al.4.00
[abs]SPLICE: Structured Prompt Local Iterative Combinatorial EvolutionDr. Anish Acharya, Phillip Studans, Amit Dhanda et al.4.00
[abs]Test-Time Graph Recalibration: Enhancing Robust Zero-Shot Inference for Graph Foundation ModelsChunchun Chen, Zhen Luo, Xing Wei et al.4.00
[PDF]Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent ReliabilityHarsh Raj, Niranjan Orkat, Suvrorup Mukherjee et al.4.00
[abs]NeuralFieldManifold: Reconstruction of LFP manifold with Lag EmbeddingKasra Fallah, Haoyu N Chen, Rudramani Singha et al.4.00
[PDF]Improving Audit Realism with Inference-Time Compute and Deployment ScaffoldsAxel Ahlqvist, Richard Guan, Juan-Pablo Rivera et al.4.00
[abs]MPQ: A Message-Passing View of Post-Training QuantizationYanshuo Chen, chenxi liu, Reza Shirkavand et al.4.00
[abs]Robust Concept Unlearning in Diffusion Models via Directional Stability RegularizationBo-Han Lai, Hsuan-Tien (Tien) Lin, Chia-Mu Yu et al.4.00
[abs]CutAttn: Discovering Cognitive Transition Layers for Efficient Long-Context PrefillingWentao Liu, Xiabao Wu, Yongchao Liu et al.4.00
[abs]mmLIP: mmWave Radar-Language Interactive Pretraining via Point ConfidenceJeongwan Shin, Jaehyeon Kim, Jae-Ho Choi4.00
[abs]CUVET: A Partitioning Approach for Continuous Treatment Assignment At ScaleArtem Betlei, Mariia Vladimirova, Victor Girou et al.4.00
[abs]Continuously-Augmented Hybrid Masked Diffusion Model for Data ImputationKijung Jeon, Molei Tao4.00
[PDF]Monitoring Violations of Differential Privacy over TimeÖnder Askin, Tim Kutta, Holger Dette4.00
[abs]Gradient Descent on Two ReLU Neurons: Global Landscape and Bifurcation DynamicsBinghua Li, Mengzhe Li, Denny Wu et al.4.00
[PDF]Why Deterministic PRM Guidance Underperforms in Discrete Diffusion ReasoningYan Zhan, Shaobo Liu, Zhijun Gao4.00
[abs]Cheap Per-Component Testing for PLS, Stable Under RotationPaweł Lenartowicz, Hubert Plisiecki4.00
[abs]Online Change-point Detection using Foundation Probabilistic Forecasting ModelsAlan Moore, Zhengyuan Zhu, Lynna Chu4.00
1 If this project is interesting to you, reach out at [email protected].