On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
Paper • 2606.00135 • Published • 1
Tong Liu
tongliuphysics
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B updated a model 9 days ago
tongliuphysics/qwen3-4b-opd4-280 published a model 9 days ago
tongliuphysics/qwen3-4b-opd4-280Organizations
upvoted a paper 12 days ago
upvoted 3
papers 3 months ago
Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the "right reasons"?
Paper • 2311.09325 • Published • 1
Multimodal Pragmatic Jailbreak on Text-to-image Models
Paper • 2409.19149 • Published • 1
FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings
Paper • 2501.06645 • Published • 1