Computer Science

POLO: An LLM-Powered Project-Level Code Performance Optimization Framework IJCAI 2025 Polynomial low degree hardness for Broadcasting on Trees (Extended Abstract) COLT 2025 Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems ICML 2025 Poplar: Efficient Scaling of Distributed DNN Training on Heterogeneous GPU Clusters AAAI 2025 POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval ICML 2025 Position: AI Agents Need Authenticated Delegation ICML 2025 Position: Future Research and Challenges Remain Towards AI for Software Engineering ICML 2025 Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AI ICML 2025 Position: Machine Learning Models Have a Supply Chain Problem ICML 2025 PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation CVPR 2025 PoWER Never Corrupts: Tool-Agnostic Verification of Crash Consistency and Corruption Detection OSDI 2025 PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides EMNLP 2025 PQR: Improving Dense Retrieval via Potential Query Modeling ACL 2025 Practical Solutions to Practical Problems in Developing Argument Mining Systems ACL 2025 Practical Solutions to the Relative Pose of Three Calibrated Cameras CVPR 2025 PreAcher: Secure and Practical Password Pre-Authentication by Content Delivery Networks NSDI 2025 Pre-Assignment Problem for Unique Minimum Vertex Cover on Bounded Clique-Width Graphs AAAI 2025 Pre-Capture Privacy via Adaptive Single-Pixel Imaging WACV 2025 Precarity and Solidarity: Preliminary Results on a Study of Queer and Disabled Fiction Writers’ Experiences with Generative AI IJCAI 2025 Predicting quantum channels over general product distributions COLT 2025 Predicting the Original Appearance of Damaged Historical Documents AAAI 2025 Prediction-Based Adaptive Variable Ordering Heuristics for Constraint Satisfaction Problems AAAI 2025 PrEditor3D: Fast and Precise 3D Shape Editing CVPR 2025 Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models AISTATS 2025 Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All ICML 2025