Haoli Bai

baihaoli's activity

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

upvoted a paper about 15 hours ago

Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models

Paper • 2508.09874 • Published Aug 13, 2025 • 13

upvoted a collection 6 days ago

Lego-RL

Collection

Harness-native RL for coding agents: the trained policy and the training task index. • 5 items • Updated 1 day ago • 11

upvoted 2 papers 6 days ago

SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review

Paper • 2607.06065 • Published Jul 7 • 11

LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents

Paper • 2608.17393 • Published 8 days ago • 24

updated a collection 16 days ago

Lego-RL

Collection

Harness-native RL for coding agents: the trained policy and the training task index. • 5 items • Updated 1 day ago • 11

updated a model 16 days ago

Lego-X/qwen3_5_35b_a3b_base_ohsdk_200k_rl

Text Generation • 36B • Updated 1 day ago • 200 • 2

updated a dataset 19 days ago

Lego-X/Lego-RL-2699

Viewer • Updated 24 minutes ago • 2.7k • 42 • 2

liked 3 datasets 3 months ago

Lego-X/Terminal-Lego-15k

Preview • Updated Jun 4 • 5.07k • 5

Lego-X/Terminal-Lego-Traj-8k

Viewer • Updated Jun 1 • 33.2k • 113 • 3

AlienKevin/SWE-ZERO-12M-trajectories

Viewer • Updated May 14 • 12.3M • 2.84k • 129

liked a dataset 5 months ago

ronantakizawa/github-codereview

Viewer • Updated Mar 10 • 356k • 737 • 60

liked 2 models 7 months ago

Lego-X/SWE-Lego-Qwen3-32B

677k • Updated Jan 13 • 45 • 5

Lego-X/SWE-Lego-Qwen3-8B

308k • Updated Jan 13 • 8.58k • 7

upvoted a paper 7 months ago

Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone

Paper • 2512.22615 • Published Dec 27, 2025 • 51

liked 2 datasets 7 months ago

Lego-X/SWE-Lego-Synthetic-Data

Viewer • Updated Jan 8 • 11.5k • 448 • 5

Lego-X/SWE-Lego-Real-Data

Viewer • Updated Jan 13 • 18k • 794 • 4

upvoted a paper 8 months ago

SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving

Paper • 2601.01426 • Published Jan 4 • 25

liked 2 datasets about 1 year ago

JierunChen/MathVista_with_difficulty_level

Viewer • Updated Jul 11, 2025 • 1k • 57 • 1

JierunChen/Ref-L4

Viewer • Updated Jun 5, 2024 • 45.3k • 419 • 10