5 papers
PERFOPT-Bench: Evaluating Coding Agents on Software Performance Optimization
Yingyun Cui, Yi Xie, Piaohong Wang +3
Coding-agent benchmarks have largely measured whether agents can produce functionally correct patches, but production software also demands measurable speedups on real execution ta…
O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
Piaohong Wang, Motong Tian, Jiaxian Li +8
Recent advancements in LLM-powered agents have demonstrated significant potential in generating human-like responses; however, they continue to face challenges in maintaining long-…
Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model
Xinyue Zhang, Haolong Li, Jiawei Ma +1
Vectorized glyphs are widely used in poster design, network animation, art display, and various other fields due to their scalability and flexibility. In typography, they are often…
Element2Vec: Build Chemical Element Representation from Text for Property Prediction
Yuanhao Li, Keyuan Lai, Tianqi Wang +3
Accurate property data for chemical elements is crucial for materials design and manufacturing, but many of them are difficult to measure directly due to equipment constraints. Whi…
Explaining Domain Shifts in Language: Concept erasing for Interpretable Image Classification
Zequn Zeng, Yudi Su, Jianqiao Sun +6
Concept-based models can map black-box representations to human-understandable concepts, which makes the decision-making process more transparent and then allows users to understan…