1 citations · 1 across the 4 of their papers we have counts for
7 papers
DIGEST: Discovery-Guided LLM Tuning for Symbolic Regression
Kaifeng Jin, Ruizhong Qiu, Zihao Li +5
Symbolic regression (SR) seeks to discover mathematical expressions directly from data, without requiring task-specific scientific descriptions. Despite tremendous progress in both…
Towards a Learnable Retriever for Textual Graph Question Answering
Kaifeng Jin, Yuchen Yan, Zhichen Zeng +4
Textual graph question answering (GraphQA) and graph-based retrieval-augmented generation (GraphRAG) have gained increasing attention as a way to ground large language models (LLMs…
VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness
Zihao Lin, Haoyu Dong, Haobo Xu +10
LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reasoning, and memory. Recursive h…
EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents
Xuying Ning, Dongqi Fu, Tianxin Wei +17
Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, recover from failures, and reuse experience across extended interactions.…
Code as Agent Harness
Xuying Ning, Katherine Tieu, Dongqi Fu +39
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineerin…
Deceptive Fairness Attacks on Graphs via Meta Learning
Jian Kang, Yinglong Xia, Ross Maciejewski +2
We study deceptive fairness attacks on graphs to answer the following question: How can we achieve poisoning attacks on a graph learning model to exacerbate the bias deceptively? W…
Hierarchical Multi-Marginal Optimal Transport for Network Alignment
Zhichen Zeng, Boxin Du, Si Zhang +3
Finding node correspondence across networks, namely multi-network alignment, is an essential prerequisite for joint learning on multiple networks. Despite great success in aligning…