Tianpeng Bu's picture

3 1

Tianpeng Bu

smallnono

·

AI & ML interests

Multimodal, CV

Recent Activity

authored a paper 1 day ago

Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization

authored a paper 1 day ago

Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents

upvoted a paper 1 day ago

Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents

View all activity

Organizations

None yet

upvoted 2 papers 1 day ago

Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents

Paper • 2605.29447 • Published 2 days ago • 12

Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization

Paper • 2605.28109 • Published 3 days ago • 17

upvoted a paper 4 months ago

D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use

Paper • 2602.02160 • Published Feb 2 • 14