Pengfei Liu

Pengfei's activity

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

upvoted a paper 17 days ago

Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training

Paper • 2602.07824 • Published 26 days ago • 16

upvoted a paper 21 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 Feb 1 • 2

upvoted a paper 30 days ago

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

Paper • 2602.02619 • Published Feb 2 • 50

upvoted 2 papers about 1 month ago

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

Paper • 2601.18418 • Published Jan 26 • 126

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

Paper • 2601.11044 • Published Jan 16 • 34

upvoted a paper 2 months ago

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

Paper • 2512.23576 • Published Dec 29, 2025 • 65

upvoted a paper 5 months ago

LIMI: Less is More for Agency

Paper • 2509.17567 • Published Sep 22, 2025 • 104

upvoted a paper 7 months ago

Complex Logical Instruction Generation

Paper • 2508.09125 • Published Aug 12, 2025 • 40

upvoted a paper 8 months ago

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling

Paper • 2506.20512 • Published Jun 25, 2025 • 47

upvoted a paper 9 months ago

Thinking with Generated Images

Paper • 2505.22525 • Published May 28, 2025 • 15

upvoted a paper 11 months ago

Generative AI Act II: Test Time Scaling Drives Cognition Engineering

Paper • 2504.13828 • Published Apr 18, 2025 • 18

upvoted 2 papers about 1 year ago

LIMO: Less is More for Reasoning

Paper • 2502.03387 • Published Feb 5, 2025 • 62

PC Agent: While You Sleep, AI Works -- A Cognitive Journey into Digital World

Paper • 2412.17589 • Published Dec 23, 2024 • 14

upvoted 3 papers over 1 year ago

O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?

Paper • 2411.16489 • Published Nov 25, 2024 • 45

Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale

Paper • 2409.17115 • Published Sep 25, 2024 • 64

OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

Paper • 2406.12753 • Published Jun 18, 2024 • 17

upvoted a paper about 2 years ago

Alignment for Honesty

Paper • 2312.07000 • Published Dec 12, 2023 • 15