Lizi Liao

Smarter Not Harder: Generative Process Evaluation with Intrinsic-Signal Driving and Ability‑Adaptive Reward Shaping

UniVA: Universal Video Agents towards Next-Generation Video Intelligence

CharLuMA: Efficient Multi-Language Chart-to-Code Generation with Low-Rank Subspace Adaptation

Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution

MeMAD: Structured Memory of Debates for Enhanced Multi-Agent Reasoning

FinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning

Look, Compare and Draw: Differential Query Transformer for Automatic Oil Painting

ConvINT: A Semi-Structured Intention Framework for Conversational Understanding

Grounding is All You Need? Dual Temporal Grounding for Video Dialog