3 11

Jiarong Liang

lllqaq

https://dream233.github.io/

AI & ML interests

Large Language Models (LLMs) Natural Language Processing (NLP)

Recent Activity

updated a model 6 days ago

lllqaq/Qwen2.5-Coder-7B-SWEsmith-400

published a model 6 days ago

lllqaq/Qwen2.5-Coder-7B-SWEsmith-400

upvoted a paper 13 days ago

STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?

View all activity

Organizations

updated a model 6 days ago

lllqaq/Qwen2.5-Coder-7B-SWEsmith-400

Text Generation • 8B • Updated 6 days ago • 34

published a model 6 days ago

lllqaq/Qwen2.5-Coder-7B-SWEsmith-400

Text Generation • 8B • Updated 6 days ago • 34

upvoted a paper 13 days ago

STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?

Paper • 2605.06527 • Published 24 days ago • 44

upvoted a paper 22 days ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 28 days ago • 116

updated a model 25 days ago

lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155

Text Generation • 1.12M • Updated 25 days ago • 22

published a model 25 days ago

lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155

Text Generation • 1.12M • Updated 25 days ago • 22

upvoted a paper 29 days ago

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Paper • 2604.28185 • Published about 1 month ago • 90

updated a collection about 1 month ago

VisPhyWorld

Collection

An execution-based framework that evaluates physical reasoning by generating executable simulator code from visual inputs. • 5 items • Updated Apr 29

updated a dataset about 1 month ago

TIGER-Lab/VisPhyWorld-Sub-All

Updated Apr 29 • 1.76k

published a dataset about 1 month ago

TIGER-Lab/VisPhyWorld-Sub-All

Updated Apr 29 • 1.76k

updated a model about 1 month ago

lllqaq/Qwen2.5-Coder-14B-Instruct-num11_v1-v2-v3-pairs-v3-triples-rope1mfix

Text Generation • 15B • Updated Apr 28 • 186 •

published a model about 1 month ago

lllqaq/Qwen2.5-Coder-14B-Instruct-num11_v1-v2-v3-pairs-v3-triples-rope1mfix

Text Generation • 15B • Updated Apr 28 • 186 •

updated a model about 1 month ago

lllqaq/SWE_Next_14B

Text Generation • 841k • Updated Apr 27 • 2

published a model about 1 month ago

lllqaq/SWE_Next_14B

Text Generation • 841k • Updated Apr 27 • 2

updated a collection about 1 month ago

VisPhyWorld

Collection

An execution-based framework that evaluates physical reasoning by generating executable simulator code from visual inputs. • 5 items • Updated Apr 29

updated a Space about 1 month ago

VisPhyWorld Comparator

🎞

Compare ground-truth and generated videos sample by sample

published a Space about 1 month ago

VisPhyWorld Comparator

🎞

Compare ground-truth and generated videos sample by sample

updated a collection about 1 month ago

VisPhyWorld

Collection

An execution-based framework that evaluates physical reasoning by generating executable simulator code from visual inputs. • 5 items • Updated Apr 29

updated a dataset about 1 month ago

TIGER-Lab/VisPhyWorld-Sub-Generated-Videos

Viewer • Updated Apr 22 • 2.52k • 1.36k

published a dataset about 1 month ago

TIGER-Lab/VisPhyWorld-Sub-Generated-Videos

Viewer • Updated Apr 22 • 2.52k • 1.36k

Jiarong Liang

AI & ML interests

Recent Activity

Organizations

lllqaq's activity

VisPhyWorld Comparator

VisPhyWorld Comparator