ElvinDu

ElvinDu518's activity

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

updated a collection 2 days ago

Lego-RL

Collection

Harness-native RL for coding agents: the trained policy and the training task index. • 6 items • Updated 2 days ago • 11

New activity in Lego-X/Lego-RL-SWE-Bench-Verified 2 days ago

Mirror Lego-RL-2699 layout: add official source view, rename eval index, rewrite README

#2 opened 2 days ago by

ElvinDu518

Add SWE-bench Verified 500 as harbor task environments + index + README

#1 opened 2 days ago by

ElvinDu518

published a dataset 2 days ago

Lego-X/Lego-RL-SWE-Bench-Verified

Viewer • Updated 2 days ago • 500 • 8

updated a model 4 days ago

Lego-X/qwen3_5_35b_a3b_ohsdk_200k_rl

Text Generation • 36B • Updated 2 days ago • 465 • 3

upvoted a paper 8 days ago

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

Paper • 2608.17393 • Published 10 days ago • 24

published a model 9 days ago

Lego-X/qwen3_5_35b_a3b_ohsdk_200k_rl

Text Generation • 36B • Updated 2 days ago • 465 • 3

published a dataset 9 days ago

Lego-X/Lego-RL-2699

Viewer • Updated 2 days ago • 2.7k • 153 • 2

upvoted a collection 9 days ago

Lego-RL

Collection

Harness-native RL for coding agents: the trained policy and the training task index. • 6 items • Updated 2 days ago • 11

authored a paper 3 months ago

MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models

Paper • 2605.14906 • Published May 14 • 79

upvoted a paper 4 months ago

MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models

Paper • 2605.14906 • Published May 14 • 79

liked a dataset 4 months ago

xiyuRenBill/MEMLENS

Viewer • Updated Jun 14 • 3.16k • 2.03k • 9

upvoted a paper 4 months ago

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

Paper • 2605.13831 • Published May 13 • 90

updated a dataset 5 months ago

ElvinDu518/harbor-rl-data

Updated Mar 30 • 479 • 1

liked a dataset 5 months ago

ElvinDu518/harbor-rl-data

Updated Mar 30 • 479 • 1

published a dataset 5 months ago

ElvinDu518/harbor-rl-data

Updated Mar 30 • 479 • 1

authored 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

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

updated a model 8 months ago

ElvinDu518/Memory-T1

Updated Dec 29, 2025 • 6

published a model 8 months ago

ElvinDu518/Memory-T1

Updated Dec 29, 2025 • 6