Pengfei Liu

Pengfei's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 3 days ago

What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom

Paper • 2602.01334 • Published 15 days ago • 2

upvoted a paper 12 days ago

daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently

Paper • 2602.02619 • Published 14 days ago • 50

published a dataset 14 days ago

GAIR/daVinci-Agency

Viewer • Updated 12 days ago • 240 • 377 • 2

liked a dataset 19 days ago

GAIR/daVinci-Dev

Viewer • Updated 16 days ago • 4.94M • 9.61k • 45

upvoted a paper 20 days ago

daVinci-Dev: Agent-native Mid-training for Software Engineering

Paper • 2601.18418 • Published 21 days ago • 124

published a model 22 days ago

GAIR/daVinci-Dev-72B

Text Generation • Updated 20 days ago • 130 • 7

published a dataset 22 days ago

GAIR/daVinci-Dev

Viewer • Updated 16 days ago • 4.94M • 9.61k • 45

upvoted a paper 27 days ago

AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts

Paper • 2601.11044 • Published Jan 16 • 34

authored a paper 28 days ago

One Sample to Rule Them All: Extreme Data Efficiency in RL Scaling

Paper • 2601.03111 • Published Jan 6 • 10

upvoted a paper about 2 months ago

LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation

Paper • 2512.23576 • Published Dec 29, 2025 • 65

liked a dataset 5 months ago

GAIR/LIMI

Viewer • Updated Oct 9, 2025 • 78 • 160 • 22

liked a model 5 months ago

GAIR/LIMI

Text Generation • Updated Oct 14, 2025 • 10 • 31

upvoted a paper 5 months ago

LIMI: Less is More for Agency

Paper • 2509.17567 • Published Sep 22, 2025 • 104

upvoted a paper 6 months ago

Complex Logical Instruction Generation

Paper • 2508.09125 • Published Aug 12, 2025 • 40

authored 6 papers 8 months ago

MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation

Paper • 2406.05690 • Published Jun 9, 2024

BeHonest: Benchmarking Honesty of Large Language Models

Paper • 2406.13261 • Published Jun 19, 2024

FRoG: Evaluating Fuzzy Reasoning of Generalized Quantifiers in Large Language Models

Paper • 2407.01046 • Published Jul 1, 2024

Halu-J: Critique-Based Hallucination Judge

Paper • 2407.12943 • Published Jul 17, 2024

Weak-to-Strong Reasoning

Paper • 2407.13647 • Published Jul 18, 2024

Understanding Reference Policies in Direct Preference Optimization

Paper • 2407.13709 • Published Jul 18, 2024 • 17