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]PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded ToolsYusheng Li, Tianjun Feng, Yunfeng Chen et al.
[abs]Scaling Point-in-Time Language Models: Economic Evaluation of EmbeddingsBryan Kelly, Semyon Malamud, Johannes Schwab et al.
[PDF]Signature-Kernel Evaluation Metrics for Robust Probabilistic and Tail-Event ForecastingBenjamin R Redhead, Thomas L Lee, Peng Gu et al.
[PDF]Watermarking Without Standards Is Not AI GovernanceAlexander Nemecek, Yuzhou Jiang, Erman Ayday
[PDF]RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust VulnerabilitiesTarek Elsayed, Shiping Yang, Eunsong Koh et al.
[PDF]Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object SegmentationJihwan Hong, Woohyeon Park, Jaeik Kim et al.
[abs]Exploring the Limits of Compositional Generalization in Vision-Language-Action ManipulationXupeng Zhang, Yantai Yang, Chang Guo et al.
[abs]Position: Machine Learning Models for Reaction Transition States Deserve BetterAtharva Tambat, Ankit Ghosh, Swastik Kumar et al.
[abs]Auditing Attention Head Masking for Out-of-Distribution Detection: Cross-Architecture Wins, Failures, and Polarity InversionsVishnu Bindu Balachandran
[abs]MetaPI: Constructing Prompt Injection Benchmarks from Any Agent BenchmarksPeiran Wang, Chong Xiang, Wenjie Qu et al.
[abs]FrameSelect: A Unified Library for Video Frame Selection and EvaluationArihant Jain, Chaosheng Dong
[abs]MEV: A Multi-Event Video Dataset for Long-Take GenerationPeiyuan Zhu, Shaoan Xie, Yifan Shen et al.
[abs]How Private is Private? A Comparative Study for Face De-IdentificationHui Wei, Hao Yu, Hui Kuurila-Zhang et al.
[PDF]Skill-Inject: Measuring Agent Vulnerability to Skill File AttacksDavid Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi et al.
[PDF]ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?Zhun Wang, Nico Schiller, Hongwei Li et al.
[PDF]Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move SequencesBenjamin Walker, Terry Lyons
[PDF]L-FAME: Longitudinal Focused Attention Meditation EEG Dataset and BenchmarkAngqi Li, Basit R Syed, Hamzeh Alzweri et al.
[abs]ALTER: An Allen's Algebra-Based Evaluation Framework for Temporal Reasoning of LLMsZhou Hongkai, Yanhui Li
[abs]Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHubEunsu Kim, Haneul Yoo, Guijin Son et al.
[PDF]ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-MakingLiu Dai, Haina Wang, Weikang Wan et al.
[PDF]On Data Engineering for Scaling LLM Terminal CapabilitiesRenjie Pi, Grace Lam, Mohammad Shoeybi et al.
[PDF]Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful EnvironmentsParth Asawa, Christopher M Glaze, Gabriel Orlanski et al.
[PDF]OgBench: A Framework for Evaluating Graph Neural Networks on Omics DataLouisa Cornelis, Johan Mathe, Louis Van Langendonck et al.
[abs]KNN Implementation Details Can Dramatically Change Performance: An Example from Cover TreesAmol Khanna, Edward Raff
[PDF]TasteBench: multimodal benchmark for sensory prediction, from molecules to sustainable foodsAnna Thomas, Sohum Patnaik, Caroline Cotto et al.
[abs]Reinforcement Learning Agents Are SwimmersJuan Rojas, Jacob Adamczyk, Abhishek Naik et al.
[abs]EpistasisBench: Revealing Structural Limitations of Zero-Shot Protein Language ModelsJunan Chen, jianwen Min, Liang He et al.
[PDF]OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin VocalizationsFaadil Mustun, Chiara Semenzin, Roberto Dessi et al.
[PDF]Standardization of Post-Publication Code Verification is Possible with the Support of the CommunitySusana López-Moreno, Eric R Dolores-Cuenca, Sangil Kim
[abs]ANCHOR: Audio-Visually Grounded Chain-of-Thought Reasoning BenchmarkJoel Julin, Souraja Kundu, Liza Dahiya et al.
[PDF]Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-benchQingyun Zou, Feng Yu, Hongshi Tan et al.
[abs]HearSayBench: Can LLMs Navigate from Abstract Human Rights to Lived Lives?Sobhan Lotfi, Ava Iranmanesh, Ali Iranmanesh et al.
[PDF]TRACE: Tourism Recommendation with Accountable Citation EvidenceZixu Zhao, SIJIN WANG, Yu Hou et al.
[PDF]Position: Let’s Strengthen Verifiability if We Can’t Enforce ReproducibilitySamet Hicsonmez, Nermin Samet, Renaud Marlet
[PDF]Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond CorrectnessIvo Petrov, Jasper Dekoninck, Dimitar I. Dimitrov et al.
[abs]Generalization Measures for Deep Learning Should Be Audited for FragilityShuofeng Zhang, Ard Louis
[abs]Don't Deploy Fine-Tuned Genomic Foundation Models Without Privacy Evaluation: Reconstruction Vulnerability Is Unpredictable Without Empirical MeasurementReem Al-Saidi, Erman Ayday, Ziad Kobti
[PDF]Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation UncertaintySarina Penquitt, Jonathan Klees, Antonia van Betteray et al.
[PDF]SLVMBench: Skill Learning from Video MemoryYudong Yang, Guangzhi Sun, Yixuan Li et al.
[PDF]Brittlebench: Quantifying LLM robustness via prompt sensitivityAngelika Romanou, Mark Ibrahim, Candace Ross et al.
[abs]Cosine is Human: The Reproducibility Ceiling of Perceptual SimilarityBenjamin TenWolde, Virginia de Sa
[abs]SignalBench: Comparing Dense Feedback Methods for Long-Horizon AgentsSergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina et al.
[PDF]Can We Trust Item Response Theory for AI Evaluation?Han Jiang, Sunbeom Kwon, Jinwen Luo et al.
[PDF]Embracing Evolution: A Call for Body-Control Co-Design in Embodied Humanoid RobotGuiliang Liu, Bo Yue, Yi J Kim et al.
[PDF]DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image ModelsWang Juntong, Wang Jiarui, Huiyu Duan et al.
[PDF]The Road Ahead in Autonomous Driving: The KITScenes Multimodal DatasetRichard Schwarzkopf, Fabian Immel, Alexander Blumberg et al.
[abs]Evaluating Depth and Breadth in Test-Time Scaling for Compositional Visual GenerationShantanu Jaiswal, Mihir Prabhudesai, Nikash Bhardwaj et al.
[PDF]ViDiC: Video Difference CaptioningJiangtao Wu, Shihao Li, Zhaozhou Bian et al.
[PDF]A systematic evaluation of vision-language models for observational astronomical reasoning tasksWenke Ren, Hengxiao Guo, Wenwen Zuo et al.
[abs]BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical LaboratoriesFei Lin, Tengchao Zhang, Ziyang Gong et al.
1 If this project is interesting to you, reach out at [email protected].