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]Causal-VLM: Dense Causal Captioning in VideosAsmar Nadeem, Mahrukh Awan, Muhammad Awais et al.
[abs]Claims of AI emergence should be grounded in information decompositionChristoph Riedl, Fernando Rosas
[PDF]RealityTest: How People Probe AI Identity and Whether Models Disclose ItAnna Gausen, Sarenne Wallbridge, Bessie O'Dell et al.
[abs]A New Perspective on XAI: Scientific Theory Building for Auditable ArtefactsSebastian R. Müller, Vanessa Toborek, Tamas Horvath et al.
[abs]TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning DevelopmentJiarui Yan, Weiwei Sun, Sijie Li et al.
[abs]MutQA: A Cross-Validated Q&A Dataset for Genetic MutationsRobert McCourt, Oladimeji Macaulay, David Arredondo et al.
[PDF]SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility ConditionsJeremy S G Yee, Daniel Zhengkui Wang, Zhiyuan Zhang et al.
[PDF]scShapeBench: Discovering geometry from high dimensional scRNAseq dataAndrew J Steindl, Joao Felipe Rocha, Brian T Di Bassinga et al.
[abs]Are LLM Safety Judges Policy-Invariant? A Three-Principle Stress-TestShihao Weng, Yang Feng, Xiaofei Xie
[abs]CoilStellaration: A Dataset and Benchmark for Engineering-Aware Stellarator Coilset GenerationJan-Hendrik Ewers, Santiago Cadena, Nicolò Foppiani et al.
[PDF]SourceBench: Can AI Answers Reference Quality Web Sources?Hexi Jin, Xurui Liu, Yuheng Li et al.
[abs]How Complete Should a Reference Be? A Benchmark Audit for Fluorescence Spot DetectionJiyeong Kong, Pan-Gyun Jeong, Kyung-Tae Kang
[abs]Evaluating an Evaluation: Membership Inference Attacks as Machine Unlearning DiagnosticsUmid Suleymanov, Laman Aliyeva, Nihat Abdullayev et al.
[abs]Stop Quantum Machine Learning; do AI-for-Quantum insteadziqing Guo, Ziwen Pan
[PDF]FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search DynamicsQiran Zou, Hou Hei Lam, Wenhao Zhao et al.
[abs]VisEditBench: A Benchmark for Vector-Format Diagram Editing with Visual InstructionsAkito Taneguchi, Itsumi Saito, Haruto Yoshida et al.
[PDF]AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic ManipulationMingyang Li, Haofan Xu, Haowen Sun et al.
[abs]Auditing Closed-Loop Learning in Recurrent Neural Networks: Reproduction, Robustness, and GeneralizationAarav Sinha
[abs]Claude Coke: Prevent Automated Crime by AgentsGabor Hollbeck, Baran Peters, Alexander von Recum et al.
[abs]RecoverBench: A Systematic Benchmark for Error Recovery in Robotic ManipulationZijia Tang, Ganlong Zhao, Xingping Chen et al.
[abs]Causal Benchmarks for Multimodal AI Should Measure Categorical Difference, Not Capability GapChinh Hoang, Mohammad Hasan
[PDF]TerminalWorld: Benchmarking Agents on Real-World Terminal TasksZhaoyang Chu, Jiarui Hu, Xingyu Jiang et al.
[abs]FlareReal: A Real-Captured Paired Dataset for Nighttime Lens Flare RemovalDafeng Zhang, Shizhuo Liu
[PDF]PitchBench: Measuring Pitch Hearing in Audio-Language ModelsMilan Liessens Dujardin, Song-Ze Yu, Craver C Thomas-Smith et al.
[PDF]HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware AnalysisHan Chen, Hanchen Wang, Hongmei Chen et al.
[abs]WordEval: Evaluating Word-Native Operation Fidelity in Document EditingJinyoung Park, Yupan Huang, Shimin Zhang et al.
[PDF]PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry PredictionZhiwen Yang, Pan Liu, yifan Li et al.
[abs]MDMR-Bench: A Multi-Dimensional Benchmark for Multi-Reference Image GenerationBowen Zheng, Jintao Lin, Chang-Heng Yi et al.
[abs]GT-Free OCR Metrics: A Reference-Free Evaluation Framework for Document OCR SystemsKshitij Singh
[abs]OpenBrain: An Auditable Generated-Label Release for Whole-Brain MRI ParcellationQizhen Lan, Yu-Chun Hsu, YUXIANG WEI et al.
[PDF]EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive EconomiesXueyu Hu, Jinxiang Xia, Shengze Xu et al.
[abs]Beyond Risky Activities: Bridging the Supervision Gap for Situational Risk ReasoningZelin Li, Yifan Liu, Ruichen Yao et al.
[PDF]MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory WritingNishant Bhargava, Rodrigo S Barrento
[PDF]RescueBench: Can Embodied Agents Save Lives in the Wild?Kui Wu, Beiyu Guo, Hao Chen et al.
[PDF]SGNNBench: A Holistic Evaluation of Spiking Graph Neural Networks on Large-scale GraphsHuizhe Zhang, Jintang Li, Yuchang Zhu et al.
[abs]The Window for Preventive Action Before AI Saturates Most Cognitive Benchmarks is ClosingJérémy Andréoletti, Antoine Maier, Laura Domenech et al.
[abs]SwitchLingua V2: Agent-Driven Code-Switching via Digital ClonesPeng Xie, Yequan Bie, Jianda Mao et al.
[PDF]AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question AnsweringChanhee Park, Jeongho Yoon, Sungbin Han et al.
[abs]Benchmarking Vietnamese Legal Knowledge of Large Language ModelsDong Nguyen Tien, Nguyen Minh-Anh, Thanh D Hoang et al.
[PDF]ConnectomeBench2: A Unified Benchmark for Automated Connectomic ProofreadingJeff Brown, Tim Farkas, Gleb Razgar et al.
[abs]When the Most Disruptive Messages Are Safe to Prune in Aggregate: Functional Analysis of Communication Pruning in Two-Agent LLM SystemsZhen Sun, Xueyang Zhou, Yongchao Chen
[PDF]CUDABeaver: Benchmarking LLM-Based Automated CUDA DebuggingShiyang Li, Haoyang Chen, Mattia Fazzini et al.
[PDF]AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose EstimationChen Si, Yulin Liu, Bo Ai et al.
[abs]ImageNet FID is a Pass Check, Not a Finish LineQinyu Zhao, Guangting Zheng, Caixia Zhou
[PDF]VocalCoachBench: Benchmarking Audio-Language Models on Expert Feedback for SingingHayeon Bang, Hounsu Kim, Wonil Kim et al.
[PDF]HSCO-Bench: An Agent-Driven End-to-End Hardware-Software Co-design Benchmark for Systems-on-ChipPei-Huan Tsai, Kuan-Lin Chiu, William Baisi et al.
[abs]OverLay++: Dense-Overlap Layout-to-Image Generation DatasetShivansh Aggarwal, Shresth Grover, Divyansh Srivastava et al.
[abs]VIPBench: A Human-Aligned Benchmark for Voice Identity Perception in the Age of Voice CloningXudong Tang, Matthew Groh
[abs]The Post-Training Dilemma: Why We Should Rethink the Sequential SFT-RL ParadigmXueyan Niu, Bo Bai, Wei Han et al.
1 If this project is interesting to you, reach out at [email protected].