Jiashuo Liu

FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

Tables2Traces: Distilling Tabular Data to Improve LLM Reasoning in Healthcare

DiscoX: Benchmarking Discourse-Level Translation in Expert Domains

Community-Aware Hard Subgraph Mining for Out-of-Distribution Generalization

Beyond Score: A Multi-Agent System to Discover Capability and Behavioral Weaknesses in LLMs

Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph

Going Beyond Static: Understanding Shifts with Time-Series Attribution

Error Slice Discovery via Manifold Compactness

LLM Embeddings Improve Test-Time Adaptation to Tabular $Y|X$-Shifts