Zhaopeng Tu's picture

4 4 1

Zhaopeng Tu

zptu

·

http://www.zptu.net

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

Deep Research: A Systematic Survey

commented on a paper about 2 months ago

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

authored a paper about 2 months ago

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

View all activity

Organizations

None yet

commented 3 papers about 2 months ago

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

Paper • 2511.04962 • Published Nov 7, 2025 • 54 •

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

Paper • 2511.04962 • Published Nov 7, 2025 • 54 •

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

Paper • 2511.04962 • Published Nov 7, 2025 • 54 •

commented a paper 3 months ago

BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs

Paper • 2509.26514 • Published Sep 30, 2025 • 3 •

commented 3 papers 11 months ago

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Paper • 2501.18585 • Published Jan 30, 2025 • 61 •

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Paper • 2501.18585 • Published Jan 30, 2025 • 61 •

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Paper • 2501.18585 • Published Jan 30, 2025 • 61 •

commented a paper about 1 year ago

Critical Tokens Matter: Token-Level Contrastive Estimation Enhence LLM's Reasoning Capability

Paper • 2411.19943 • Published Nov 29, 2024 • 62 •