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]MEMEVO: A Memory-Evolved Video Agent for Long Video UnderstandingYuan Wang, Yake Wei, Tianrun Xu et al.4.33
[PDF]DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNsDaewon Chae, Hyunwon Chung, Changwoo Lee et al.4.33
[PDF]UNICOM: Unified Multimodal Modeling via Compressed Continuous Semantic RepresentationsYaqi Zhao, Wang Lin, Zijian Zhang et al.4.33
[PDF]The Alignment Illusion in Multimodal Large Language ModelsHong-Han Wang, Yuntao Wang, Hu Ding4.33
[abs]Rethinking Gradient Approximation in Quantization: A Zeroth-Order Expectation PerspectiveWenkang Wang, Jia Zhang, Zelin Wei et al.4.33
[abs]Reading Attribution from Attention: Evidence Heads as Latent Attribution Mechanisms in LLMsQi Wu, Jianfeng Qu, Peng-Fei Zhang et al.4.33
[PDF]Video-Mirai: Autoregressive Video Diffusion Models Need ForesightYonghao Yu, Lang Huang, Runyi Li et al.4.33
[abs]TritonTune: LLM-Guided Multi-Agent Optimization of GPU Kernel ConfigurationsShukai Duan, Mihai Capotă, Guixiang Ma et al.4.33
[abs]Bridging 1D, 2D, and 3D with Any-to-Any Multimodal ModelingJason Toskov, Oriol Barbany, Rishubh Singh et al.4.33
[PDF]Scaling Causal Reasoning with Increasingly Complex Causal SimulatorsNicolás Astorga, Anita Kriz, Mihaela van der Schaar4.33
[PDF]CUDABench: Benchmarking LLMs for Text-to-CUDA GenerationJiace Zhu, Wentao Chen, Qi Fan et al.4.33
[abs]DRILL: Training World Models to Improve Policies, Not Predict PixelsZhaolu Kang, Tailong Luo, Sihan Liu et al.4.33
[abs]From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy GradientChangming Li, Kaixing Zhang, Yingdong Shi et al.4.33
[abs]Noisy isomorphism: Robust expressivity of GNNs under structural perturbationNing Zhang, Mihai Cucuringu, Xiaowen Dong4.33
[PDF]Entropy Distribution as a Fingerprint for Hallucinations in Generative ModelsMattia Jacopo Villani, Pranav Deshpande, Akshay Seshadri et al.4.33
[PDF]BarrierSteer: LLM Safety via Learning Barrier SteeringThanh Q. Tran, Arun Verma, Kiwan Wong et al.4.33
[PDF]FairMT: Fairness for Heterogeneous Multi-Task LearningGuanyu Hu, Tangzheng Lian, Na Yan et al.4.33
[abs]Your Self-Supervised Projection Head Captures Object Co-Occurrence StatisticsArthur Aubret, Jochen Triesch, Céline Teulière4.33
[abs]Walking the Hypercube: Unbiased Quantum Partition Functions Without the MatrixKumar Avinava Dubey, Arijit Sehanobish, Krzysztof M Choromanski4.33
[abs]Trajectory-Matching Meta Pseudo-Labeling for Semi-Supervised LearningMinh Duc Le, Minh-Duong Nguyen, Dung Le4.33
[abs]RAHF: Reward-Amplified Human Feedback for Closed-Loop Policy Fine-TuningHaoyuan Cai, Seth Zhao, Jason Zhang et al.4.33
[PDF]Structure-Semantic Co-optimized Latent Diffusion Model for Fast Visual Anagram SynthesisXiang Gao, Yunpeng Jia4.33
[abs]Median-of-Means under Structured Heavy-Tailed Noise: High-Probability Bounds for Clipped Stochastic OptimizationAhmed El Bajdali, Ohad Shamir, Samuel Horváth et al.4.33
[abs]MT-CC: Multi-Group Temperature Scaling for Asymmetric Calibration Behavior in Class-Incremental LearningSungjun Yun, Yonghee Choi, Dong-Jun Han4.33
[abs]Robust Offline Reinforcement Learning against Out-of-Distribution Dynamics in Autonomous DrivingHaozhe Liu, Jie Wang, Rui Yang et al.4.33
[PDF]Literati: Towards Anytime Optimal Shape Generalized Trees via AO*Nakul Upadhya, Eldan Cohen4.33
[PDF]Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit CompressionTue M Cao, Nguyen Do, My T. Thai4.33
[abs]Tree-Guided Identify Then Exploit: A Unified Framework of Pure Exploration and Regret Minimization for Dueling BanditsPu Wang, Yao-Xiang Ding4.33
[PDF]On-Policy Consistency Training Improves LLM Safety with Minimal Capability DegradationAndy Q Han, Kristina Fujimoto, Avidan Shah et al.4.33
[PDF]Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without DelaysTing Hu, Luanda Cai, Emmanouil-Vasileios Vlatakis-Gkaragkounis4.33
[PDF]Intelligence per Watt: Measuring Intelligence Efficiency of Local AIJon Saad-Falcon, Avanika Narayan, Hakki Akengin et al.4.33
[abs]Anchoring Physiological Invariance, Expanding Domain Plasticity: Prior-Stabilized Dynamic Adaptation for Continual rPPG MeasurementZhongtian He, Shuyang chu, Jingang Shi4.33
[PDF]Spectral Alignment in Forward–Backward Representations via Temporal AbstractionSeyed Mahdi Basiri Azad, Jasper Hoffmann, Iman Nematollahi et al.4.33
[PDF]PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool PlanningYu Li, Guangfeng Cai, shengtian yang et al.4.33
[abs]Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and DispersionWalid Bendada, Guillaume Salha-Galvan4.33
[PDF]Sequential Solution Concepts in Cooperative Games with Generalized Characteristic FunctionsAshwin Goyal, Drashthi Doshi, Swaprava Nath4.33
[PDF]Inverse Reinforcement Learning with Just Classification and a Few RegressionsLars van der Laan, Nathan Kallus, Aurelien Bibaut4.33
[abs]Logarithmic Depth Suffices for In-Context Gradient DescentYingze Li, Dong Wang, Xianglong Liu et al.4.33
[abs]Beyond Spatial and Temporal Priors: A Generalizable Approach for Dense Correspondence MatchingLuping Liu, Bingyi Kang, Yifan Wang et al.4.33
[PDF]Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learningPaarth Gulati, Ilya Nemenman4.33
[PDF]MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIPChau Truong, Hieu Ta, Zhenzhen Liu et al.4.33
[abs]Beyond the Full Slate: Evaluating MNL Algorithms on All SlatesFlavio Chierichetti, Mirko Giacchini, Ravi Kumar et al.4.33
[PDF]Attention as In-Context Empirical Bayes: A Two-Stage View via Particle DynamicsMatthew Smart, Soumya Ganguly, Nilava Metya et al.4.33
1 If this project is interesting to you, reach out at [email protected].