Tong Zhang
- ASGO: Adaptive Structured Gradient Optimization
- GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
- MergeBench: A Benchmark for Merging Domain-Specialized LLMs
- One for All: Universal Topological Primitive Transfer for Graph Structure Learning
- Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
- Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
- Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction
- UniHG: A Large-scale Universal Heterogeneous Graph Dataset and Benchmark for Representation Learning and Cross-Domain Transferring
- Value Diffusion Reinforcement Learning