Artificial Intelligence

2026-09-03 Mean Flows for One-step Generative Modeling
2026-07-03 The Online Reviewer Assignment Problem
2026-05-27 No Free Lunch in LLM Watermarking
2026-05-22 Crediting the Right Steps: Stepwise Reward Assignment for RL on Flow Matching Models
2026-05-15 Operator-Level Disaggregated Serving for Efficient LLM Inference
2026-04-30 Learning by Analogy for Compositional Generation
2026-04-09 CAD: Disaggregating Core Attention for Efficient Long-context Language Model Training
2025-12-14 TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
2025-12-09 LithOS: An Operating System for Efficient Machine Learning on GPUs
2025-12-04 SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications
2025-11-06 Computer Assisted Mathematics: A Case Study in Discrete Geometry
2025-10-28 On Noisy Evaluation in Federated Hyperparameter Tuning
2025-10-20 From Representation Engineering to Circuit Breaking: Toward Transparent and Safer AI
2025-06-05 The NeurIPS 2024 Paper-Reviewer Assignment Algorithm
2025-05-02 Leveraging Symmetries in Strategic Games
2025-04-28 Grounding Neural Inference with Satisfiability Modulo Theories: Leveraging Theory Solvers for Machine Learning
2025-04-28 Classical generalization theory is more predictive in foundation models than in conventional deep networks
2025-03-11 Safe Pareto improvements: Making everyone better off without taking chances
2025-01-21 Usefulness of LLMs as an Author Checklist Assistant for Scientific Papers: NeurIPS'24 Experiment
2024-11-27 Optimizing and Characterizing High-Throughput Low-Latency LLM Inference in MLCEngine
2024-11-26 Encoding Cardinality Constraints in Automated Reasoning
2024-08-23 miniCodeProps: a Benchmark for Proving Code Properties
2024-06-21 Measuring and Exploiting Network Usable Information
2024-05-05 T2FPV: Dataset and Method for Correcting First-Person View Errors in Pedestrian Trajectory Prediction
2023-10-31 Transfer Learning within a Heterogeneous Graph
2023-04-21 Robustness between the worst and average case
2023-02-21 Classification with Strategically Withheld Data
2022-01-06 Cases2Beds: A Case Study in Actionable Intelligence Highlights