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]Manifold Drift in Flow Preference Optimization: A Root Cause of Reward HackingYansen Han, Shengyi Liao, Yuanxing Zhang et al.4.00
[abs]ACQueReLlo: Alignment-Aware Constrained Quantization via Reinforcement Learning for Large Language ModelsSinuo Fan, Zirui Fu, Marco Donato et al.4.00
[PDF]FTerViT: Fully Ternary Vision TransformerSzymon Ruciński, Pietro Bonazzi, Engin Turetken et al.4.00
[abs]Mechanistic Critics for Sample-Efficient NPU Design-Space ExplorationYicheng He, Yuqi Xue, Tianyang Wu et al.4.00
[PDF]VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance ReductionXin-Qiang Cai, Masashi Sugiyama4.00
[PDF]Joint Optimization of Tool Creation and Use for Large Language Model AgentsZhi Rui Tam, Chieh-Yen Lin, Yun-Nung (Vivian) Chen et al.4.00
[PDF]What are Key Factors for Updates in RL for LLM Reasoning?Peidong Wang, Ruohan Wang, Xufang Luo et al.4.00
[PDF]Drifting Fields are not ConservativeLeonard T. Franz, Sebastian Hoffmann, Tim Weiland et al.4.00
[PDF]Interpreting Neural Combinatorial Optimization via Evolving Programmatic BottlenecksHaocheng Duan, Yuxin Guo, Jieyi Bi et al.4.00
[abs]Backdoor Attacks under Lossy Compression: From Failure to Reactivation and AdaptationQian Li, Yunuo Chen, Yuntian Chen4.00
[abs]Heuresis: Evaluating Search Strategies for Autonomous Machine Learning Research AgentsAntonis Antoniades, Deepak Nathani, Ritam Saha et al.4.00
[PDF]SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement LearningJianchang Su, Yifan Zhang, Shengkai Lin et al.4.00
[abs]Epigenomics-Guided Flow Matching for 3D Genome Super-ResolutionYubiao Zhao, Shicheng Song, Yusen Ye et al.4.00
[abs]A Computational Perspective to Data Ablation ExperimentsJiachen (Tianhao) Wang, Lin Chen, Mohammadhossein Bateni et al.4.00
[abs]Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time ReasoningWeida Liang, Kenji Kawaguchi4.00
[PDF]Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape AnalysisThong Bach, Dung Nguyen, Thao Le et al.4.00
[abs]TRACE: Trajectory-Aware Conceps for Explainable Video UnderstandingWooil Lee, Junpyo Hong, Jongseo Lee et al.4.00
[PDF]The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling LawsEslam Zaher, Maciej Trzaskowski, Quan Nguyen et al.4.00
[PDF]AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-TuningZiye Chen, Hongbin Lin, Chenyu Zhang et al.4.00
[PDF]Non-Linear Pricing Restores Tractability for a Data SellerBhaskar Ray Chaudhury, Jugal Garg, Eklavya Sharma et al.4.00
[abs]DART: Zero-Shot Dual-Side Alignment Routing for LLM Performance-Cost TradeoffsYuejun Jiao, Yanxin Yang, Boyu Wang et al.4.00
[abs]Inference-Time Self-Aligned Drifting for Few-Step Flow MatchingShigui Li, JIAN XU, Wei Chen et al.4.00
[abs]Visual-to-Executable Procedural Reconstruction of Buildings.Zichong Zhu, Zhihao Liu, Andrei Sharf et al.4.00
[abs]Market-Based Runtime Resource Allocation for LLM Multi-Agent SystemsYixue Huang, Mingxin Wang, Hao Li et al.4.00
[abs]Sparse Repair in Reasoning Traces: A Structural View of Test-Time InferenceZhuorui Zhang, Jianqi Yan, Shanshan Feng et al.4.00
[abs]Learning Data-free Universal Adversarial Perturbation with Hybrid Priors and Gradient-Guided Sharpness RegularizationZhi Tan, Jiazheng Cui, Wenwen Zhang et al.4.00
[abs]CupOFMoCA: Coupled Objective-Guided Discrete Flows for Molecular Conjugate AssemblyRuoxi Zhang, Ziang Li, Jiatao Gu et al.4.00
[abs]Class-Incremental Learning via LoRA-based Elastic Ensemble of ExpertsRuilong Yu, Fei Ye, Zhiyuan Ren et al.4.00
[PDF]Provably Reliable Classifier Guidance via Cross-Entropy ControlSharan Sahu, Arisina Banerjee, Yuchen Wu4.00
[PDF]One Model, Two Roles: Emergent Specialization in a Shared Recurrent TransformerJucheng Shen, Barbara Su, Anastasios Kyrillidis4.00
[PDF]Optimal In-context Adaptivity and Distributional Robustness of TransformersTianyi Ma, Tengyao Wang, Richard J Samworth4.00
[abs]FEROM: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMsZian Su, Ziyang Huang, Kaiyuan Zhang et al.4.00
[PDF]ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory ModelingBrian Nlong Zhao, Ozgur Kara, Junho Kim et al.4.00
[PDF]SkillOrchestra: Learning to Route Agents via Skill TransferJiayu Wang, Yifei Ming, Zixuan Ke et al.4.00
[PDF]HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial RepresentationsGuillermo Bernárdez, Marco Montagna, Louis Van Langendonck et al.4.00
[abs]Self-Recognition Finetuning can Reverse and Prevent Emergent MisalignmentArush Tagade, Shaoheng Zhou, Jiaxin Wen et al.4.00
[abs]ADMIT: Support-Gated Memory-Write Admission for Document QA AgentsJoongmin Shin, Gyuho Shim, Hyeonseok Moon et al.4.00
[PDF]Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination MitigationXin Zou, Haolin Deng, Yibo Yan et al.4.00
[PDF]COMPLLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-makingZiyang Guo, Yifan Wu, Jason Hartline et al.4.00
[abs]Seeing but Not Detecting: Privacy-Preserving Scene Text Attack via Hybrid Adversarial Policy LearningFeiran Li, Jiahao Lyu, Ke Jiang et al.4.00
[PDF]InfoSFT: Learn More and Forget Less with Information-Aware Token WeightingMahdi Sabbaghi, George J. Pappas, Adel Javanmard et al.4.00
[abs]DASM: Dynamic Autoregressive Subgraph Mining via Two-Stage Policy AlignmentYuming Huang, Haoran Yin, Wu4.00
[abs]MIND-DDI: Multi-Omics Interpretable Drug-Drug Interaction Prediction with Joint Optimization of Graph Structure, Neural Architecture, and Symbolic RulesLinxin Xiao, Xin Wang, Yang Yao et al.4.00
[abs]Learning Informative Invariant Representations via Hierarchical Latent DecompositionHyungkwon Lee, Hyewon Ryu, Jong-Seok Lee4.00
[PDF]Online Learning via Learned Latent Bayesian TrackingGuy Gerson, Tomer Raviv, Nir Shlezinger et al.4.00
[PDF]Steering Visual Generation in Unified Multimodal Models with Understanding SupervisionZeyu Liu, Zanlin Ni, Yang Yue et al.4.00
[abs]TRIDENT: Post-Selection Evidence Accountability for Token-Efficient RAGWutong Zhang, Jiong Lou, Richard Liu et al.4.00
[PDF]Tools as Continuous Flow for Evolving Agentic ReasoningTairan Huang, Siyu Shang, Qiang Chen et al.4.00
[abs]See to Believe: Segmentation by Reasoning with Visual EvidenceChangsong Wen, Yanjie Wang, Zelin Peng et al.4.00
1 If this project is interesting to you, reach out at [email protected].