14 papers
TusoAI: Agentic Optimization for Scientific Methods
Alistair Turcan, Kexin Huang, Lei Li +1
Scientific discovery is often slowed by the manual development of computational tools needed to analyze complex experimental data. Building such tools is costly and time-consuming…
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
Weimin Xiong, Shuhao Gu, Bowen Ye +5
Recent advances in multimodal large language models have driven growing interest in graphical user interface (GUI) agents, yet their generalization remains constrained by the scarc…
HSUGA: LLM-Enhanced Recommendation with Hierarchical Semantic Understanding and Group-Aware Alignment
Guorui Li, Dugang Liu, Lei Li +2
Large language model (LLM)-enhanced sequential recommendation typically aims to improve two core components: user semantic embedding extraction and utilization. Despite promising r…
BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD
Haozhe Zhang, Kaichen Liu, Miaomiao Chen +4
Industrial Computer-Aided Design (CAD) code generation requires models to produce executable parametric programs from visual or textual inputs. Beyond recognizing the outer shape o…
SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making
Zeyu Li, Lei Li
Decision making in large-scale complaint handling systems increasingly relies on heterogeneous evidence, including complaint narratives, screenshots, order metadata, historical int…
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
Yang Zhou, Can Jin, Zihan Dong +7
Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty…