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]SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure ScenariosJackson Clark, Yiming Su, Saad Mohammad Rafid Pial et al.
[PDF]Mosaic: A Benchmark Suite for Differentiable Physics SolversAndrin Rehmann, Heiko Zimmermann, Dion Häfner
[PDF]MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization ModelingZhong Li, Qi Huang, Yuxuan Zhu et al.
[abs]Adversarial Risk in the Generative AI Era Necessitates Dropping the Small Epsilon BallAndrew Cullen, Neil Marchant, Paul Montague et al.
[PDF]Where Root Cause Analysis Fails: A Retrieval-Reranking DecompositionHada Melino Muhammad, Luan Pham, Laure Barrière et al.
[PDF]VeriContest: A Competitive-Programming Benchmark for Verifiable Code GenerationZichen Xie, Mrigank Pawagi, Yuxin Liu et al.
[PDF]MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP AgentsHaonan Li, Tianjun Sun, Yongqing Wang et al.
[PDF]ITPEval: Benchmarking Formal Translation Across Interactive Theorem ProversJiayi Wu, Robert Joseph George, Animashree Anandkumar
[PDF]SciReason: A Controllable Benchmark for Scientific Reasoning in LLMsPierre Beckmann, Marco Valentino, Andre Freitas
[abs]Information Parity for Code: The Scope of Transfer in Multilingual Code ModelsAlexander Tsvetkov, Alon Kipnis
[abs]AQBENCH: Benchmarking Neural Surrogates for Air Quality ForecastingSiddharthan Dileep, Sanchit Bedi, Pareshbhai D Parmar et al.
[PDF]SETA: Scaling Environments for Terminal AgentsQijia Shen, Zhiqi Huang, Vamsidhar Kamanuru et al.
[abs]Position: Semantic Uncertainty Measures Disagreement, Not ReliabilityJoseph Hoche, Maxime Corlay, David Brellmann et al.
[abs]SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow BenchmarkTaeyoung Yu, Seonbin Jo, Jiwon Kim et al.
[PDF]CalArena: A Large Scale Post-Hoc Calibration BenchmarkEugène Berta, David Holzmüller, Francis Bach et al.
[abs]KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task RecommendationChenxu Li, Shuchang Liu, Hantao Shu et al.
[PDF]DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous DrivingAnh Hao Vo, Khoa Vo, Phu Loc Nguyen et al.
[abs]ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and ModelMinghao Xu, Jiaze Song, Jinyu Wang et al.
[abs]SituRecBench: A Benchmark for Situated Recommendation in 3D Interactive EnvironmentsJingtong Yang, Dongding LIN, Jian Wang et al.
[abs]LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image SynthesisHaoxiang Cao, Yuxuan Zhang, Penghui Du et al.
[abs]A Multimodal Benchmark for Evaluating Cause-of-Death Inference Using Child Health and Mortality DataJunhe Yang, Soumyakanti Pan, Hyun Seung Lim et al.
[abs]TSB-SEG: A Systematic Time-Series Segmentation BenchmarkFélix Chavelli, Arik Ermshaus, Patrick Schäfer et al.
[PDF]What Gets Measured Gets Managed: Sign-aware Recommendation Needs Sign-aware EvaluationMinchan Kim, Jungmin Hwang, Hyunwoo Park
[abs]OpenSanctions Pairs: A Large-Scale Dataset for Pairwise Entity MatchingChandler Smith, Magnus Sesodia, Friedrich Lindenberg et al.
[PDF]Agent Security is a Systems ProblemMihai Christodorescu, Earlence Fernandes, Ashish Hooda et al.
[abs]SafeDrug: A Benchmark Dataset for Safety-Critical Pharmacological Reasoning in LLMsTengfei Ma, Yushan Yang, HOU Jiahao et al.
[PDF]HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical DataZhenyu Zhao, Xinrui Ruan, Waverly Wei et al.
[PDF]ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image ModelsChenxi Ruan, Yihan Hou, Yu Xiao et al.
[PDF]Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?Luc Sträter, Hazel Doughty
[abs]Automated Hypothesis Discovery for Characterizing Annotation DisagreementAnkita Gupta, Alexandra Chouldechova, Alex Dow et al.
[PDF]Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic ReviewsShreyansh Padarha, Ryan Othniel Kearns, Tristan M Naidoo et al.
[PDF]Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field GamesLorenzo Magnino, Jiacheng Shen, Matthieu Geist et al.
[PDF]MDPBench: A Benchmark for Multilingual Document Parsing in Real-World ScenariosZhang Li, Lin Zhibo, Qiang Liu et al.
[PDF]SPATIALEPIBENCH: Benchmarking Spatial Information and Epidemic Priors in ForecastingRuiqi Lyu, Alistair Turcan, Bryan Wilder
[PDF]Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNsAntonis Vasileiou, Juan Cervino, Pascal Frossard et al.
[abs]CT-Lesion: A Multi-Region CT Dataset for Co-existing Lesion Segmentation and DetectionRuihan Lu, Leiqiang Pan, Shijie Wang et al.
[PDF]Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal SamplingDaniel McBride, Pratik Khandagale, Cristina Garcia-Cardona et al.
[PDF]RamanBench: A Large-Scale Benchmark for Machine Learning on Raman SpectroscopyMario Koddenbrock, Christoph Lange, Robin Legner et al.
[abs]Self-Evolving Agents Should Build Internal and External Models of the WorldLuiz Felipe Vecchietti, Bryan Nathanael Wijaya, Wenchao Dong et al.
[PDF]DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop ExecutionChengkai Xu, Jiaqi Liu, Yicheng Guo et al.
[abs]When Do Cosine Prototypes Mislead? A Whitening-Aware Benchmark for Frozen-Feature Image ClassificationJian Ding, Su Yang
[abs]Right Results, Wrong Reasons: Auditing Behavioral Reliance in Motion ForecastingGeonyeong Park, Byounghun Park, Nayoung Kim et al.
[abs]Static Recovery Is Not Dynamic Stability: Dynamics-Aware Benchmarking of Protein Motif ScaffoldingEmile de Bruyn, Moritz Schäffler, Jannik Schneider et al.
[abs]The Agentic Oversight Tax: Human Supervision of AI Agents Has a Cost that Must be Accounted ForOlivier Oullier
[PDF]Position: The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation ModelsAdam Stein, Aaditya Naik, Neelay Velingker et al.
[abs]SH: A Mathematician-Curated benchmark for Assessing Research-level Math Capabilities of LLMsGuijin Son, Seungone Kim, Catherine Arnett et al.
[PDF]Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)Zichen TANG, Zirui Zhang, Qian Wang et al.
1 If this project is interesting to you, reach out at [email protected].