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]EEG Benchmarking Needs a Task Specification Layer: NeuroDoc for Rulebook-Guided, Executable Benchmark ConstructionChengxuan Qin, 致格 陈, Pengshu et al.
[PDF]SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite ImageryJiajun Jiang, Chunliang Hua, Zichun Chen et al.
[abs]MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight PerceptionTara Boroushaki, Laura Dodds, Cusuh Ham et al.
[PDF]VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web CorporaYuting Xu, Jiayi Tian, Jian Liang et al.
[abs]BabyTheorist: A Benchmark for Learning to Theorize the World from Observation AloneDoojin Baek, Junyeob Baek, Mingyu Jo et al.
[abs]Decentralized AI Governance Must Decouple Policy Processing from Capability EnforcementHasan Kassem, Christoforos Anagnostopoulos, Alejandro Aristizabal et al.
[PDF]Agentic AI Scientists Are Not Built For Autonomous Scientific DiscoveryHarshit Bisht, Vinay Kumar, Kevin Maik Jablonka et al.
[PDF]When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use AgentsXiaolin Zhou, Aojie Yuan, Zheng Luo et al.
[abs]Prefix Executability: Evaluating Tool-Using Agents Beyond Final SuccessAmir H Rezaeian, Weiyi Sun, Yassine Benajiba et al.
[abs]Penalize to Verify: A Multi-Domain Benchmark for Trustworthy LLM EvaluationJia-chen Zhang, Zheng Zhou, Zhuo Wang et al.
[PDF]PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?Zongyi Chen, Yu Liang, Jie Lin et al.
[abs]SiliciclasticReservoirs: A Million-Reservoir Dataset and Flow-Matching Foundation Model for 3D Siliciclastic Reservoir GenerationIlgar Baghishov, Elnara Rustamzade, Graeme Henkelman et al.
[PDF]GraphIP–Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?Kaixiang Zhao, Bolin Shen, Yuyang Dai et al.
[PDF]CruxBench: A Benchmark of Information DiscoveryLina Piao, Amelia Hui Dai, Nick Merrill et al.
[PDF]AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration BenchmarkMikołaj Jastrzębski, Dawid Glinkowski, Dawid Zieliński et al.
[PDF]Multi-site PPG: An In-the-Wild Physiological Dataset from Emerging Multi-Site WearablesJiayi Shao, Jiaying Ye, ShengYao Liu et al.
[abs]VeruSAGE-Bench: A Benchmark Suite for Rust System VerificationChenyuan Yang, Natalie Neamtu, Chris Hawblitzel et al.
[PDF]Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate TokensKarthik Valmeekam, Vardhan Palod, Kaya Stechly et al.
[PDF]MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding AgentsJonathan Steinberg, Oren Gal
[abs]ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic PerspectiveChaoran Li, Yukun Li, Zeyuan Zhao et al.
[abs]fxBench: Evaluating and Understanding Formula Suggestions in SpreadsheetsSanket Mhatre, Sumit Gulwani, Vu Le et al.
[PDF]C3VD-DEFCOL: A Deformable Colonoscopy Dataset with Time-Resolved 3D Ground Truth and Realistic AppearanceEthan Luk, Mayank Golhar, Anthony Song et al.
[abs]Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-CalibrationShiqi Zhang, Weixin Zeng, Ziheng Zhang et al.
[PDF]ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text EditingXinghao Chen, Xiangbo Gao, Jiongze Yu et al.
[PDF]SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode DiagnosisRishav Pramanik, Ian Nielsen, Jeffrey Smith et al.
[abs]Multi-Oracle Agreement Reveals the Limits of Self-Consistency Evaluation in RNA DesignMinghao Sun, Hanqun Cao, Fang Wu et al.
[abs]Can VLMs Reason When to Stop for Human Safety?Ryo Hachiuma, Arun G Zachariah, Barnaby Simkin et al.
[abs]A Stratified Multi-Rater Evaluation of LLM-Based Virtual Standardized Patients with a Deployed Data-Generation PlatformYongjin Yi, JIn Yong Park, Sejoong Kim
[abs]Visual Robustness and Neural Alignment in a Shared Foraging Task: The Mouse vs. AI BenchmarkMarius Schneider, Joe Canzano, Yuchen Hou et al.
[abs]VocalGrad: Evaluating Acoustic Perception in Audio Language ModelsKoki Ryu, Hitomi Yanaka
[abs]The BAMBI Dataset: Multimodal Nadir UAV-Recordings of Forest WildlifeChristoph Praschl, Hugo Markoff, Anna Maschek et al.
[PDF]Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event ModelingYahya Aalaila, Sebastian Vollmer, Gerrit Großmann
[PDF]Crossing the Validation crisis: Cross-validation reduces benchmarking variance surprisingly wellCélestin Eve, Gael Varoquaux, Thomas Moreau
[PDF]A Large-Scale Multi-Source Dataset Linking Hacker Community Discourse to the CVE Vulnerability LifecycleBenjamin M Ampel, Sagar Samtani
[abs]CSBench: A Comprehensive Benchmark for Evaluating Project-Level System Construction in Computer ScienceHongli Yu, Huan-ang Gao, Botian Wang et al.
[abs]Your Benchmark Is an Empirical Measure Over DifficultyYifan Sun, Naicheng Yu, Jiawen Gong et al.
[abs]Concept-Based Mechanistic Interpretability Needs a Concrete Evaluation ParadigmYiming Tang, Qinglin Qi, LIN Zheng et al.
[PDF]InterLV-Search: Benchmarking Interleaved Multimodal Agentic SearchBohan Hou, Jiuning Gu, Jiayan Guo et al.
[PDF]PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems?Ruoran Xu, Wending Gao, Liyunfeng Chen et al.
[abs]An In-Depth Analysis of Hallucination Detection Methods for Vision-Language ModelsAllison Chen, William Yang, Salma Abdel Magid et al.
[abs]EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground TruthJens Parslov, Marco Schouten, Dim Papadopoulos
[abs]Large language models can not and should not be banned from peer reviewAnat Kleiman, Gustaf Ahdritz
[PDF]Attack Selection In Agentic AI Control Evaluations Meaningfully Decreases SafetyCatherine Ge-Wang, Tyler Crosse, Benjamin Hadad et al.
[abs]SWE-Pro: A Benchmark for Evaluating LLMs on Performance-Oriented Repository-Level OptimizationEzgi Sarıkayak, Wenchao Gu, Hesham Ghonim et al.
[abs]Differential Item Functioning as an Item-Level Diagnostic for LLM BenchmarksHansol Lee, Jason B Cho, Nick Haber et al.
[PDF]HalluWorld: A Controlled Benchmark for Hallucination via Reference World ModelsEmmy Liu, Varun Gangal, Michael Yu et al.
[abs]Nereus: A Large-Scale Underwater Dataset for Fine-Grained Attribute Understanding and Grounded Counting PerceptionJingtao Deng, Zihao Jin, Yuehe Chen et al.
[abs]MSConsensus: A Hundred-Million-Scale, Batch-Effect–Suppressed Dataset and Benchmark for Proteomics Machine LearningChristopher Grams, Chang Liu, Michael Papka et al.
[PDF]CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack ScenariosTaein Lim, Seongyong Ju, Munhyeok Kim et al.
[PDF]LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative ModelsLu Liu, Huiyu Duan, Chenxin Zhu et al.
1 If this project is interesting to you, reach out at [email protected].