3 9

Jiarong Liang

lllqaq

https://dream233.github.io/

AI & ML interests

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

Recent Activity

upvoted a paper 3 days ago

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

updated a collection 6 days ago

VisPhyWorld

updated a dataset 6 days ago

TIGER-Lab/VisPhyWorld-Sub-All

View all activity

Organizations

upvoted a paper 3 days ago

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

Paper • 2604.28185 • Published 5 days ago • 83

updated a collection 6 days ago

VisPhyWorld

Collection

An execution-based framework that evaluates physical reasoning by generating executable simulator code from visual inputs. • 5 items • Updated 6 days ago

updated a dataset 6 days ago

TIGER-Lab/VisPhyWorld-Sub-All

Updated 6 days ago • 79

published a dataset 6 days ago

TIGER-Lab/VisPhyWorld-Sub-All

Updated 6 days ago • 79

updated a model 7 days ago

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

Text Generation • 15B • Updated 7 days ago • 210

published a model 7 days ago

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

Text Generation • 15B • Updated 7 days ago • 210

updated a model 7 days ago

lllqaq/SWE_Next_14B

Text Generation • 841k • Updated 7 days ago • 8

published a model 7 days ago

lllqaq/SWE_Next_14B

Text Generation • 841k • Updated 7 days ago • 8

updated a collection 13 days ago

VisPhyWorld

Collection

An execution-based framework that evaluates physical reasoning by generating executable simulator code from visual inputs. • 5 items • Updated 6 days ago

updated a Space 13 days ago

VisPhyWorld Comparator

🎞

Compare ground-truth and generated videos sample by sample

published a Space 13 days ago

VisPhyWorld Comparator

🎞

Compare ground-truth and generated videos sample by sample

updated a collection 13 days ago

VisPhyWorld

Collection

An execution-based framework that evaluates physical reasoning by generating executable simulator code from visual inputs. • 5 items • Updated 6 days ago

updated a dataset 13 days ago

TIGER-Lab/VisPhyWorld-Sub-Generated-Videos

Viewer • Updated 13 days ago • 2.52k • 76

published a dataset 13 days ago

TIGER-Lab/VisPhyWorld-Sub-Generated-Videos

Viewer • Updated 13 days ago • 2.52k • 76

updated a model 15 days ago

lllqaq/Qwen2.5-Coder-14B-Instruct-num11-v1-v2-v3-pairs-v3-triples-post-rope1mfix

841k • Updated 15 days ago • 11

published a model 15 days ago

lllqaq/Qwen2.5-Coder-14B-Instruct-num11-v1-v2-v3-pairs-v3-triples-post-rope1mfix

841k • Updated 15 days ago • 11

updated a model 16 days ago

lllqaq/Qwen2.5-Coder-14B-Instruct-num11-v1-v2-v3-pairs-v3-triples-post-r2egym

Text Generation • 841k • Updated 16 days ago • 306

published a model 16 days ago

lllqaq/Qwen2.5-Coder-14B-Instruct-num11-v1-v2-v3-pairs-v3-triples-post-r2egym

Text Generation • 841k • Updated 16 days ago • 306

upvoted a paper 18 days ago

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

Paper • 2604.11626 • Published 22 days ago • 101

New activity in TIGER-Lab/packages_python_filtered 19 days ago

[bot] Conversion to Parquet

#1 opened 21 days ago by

parquet-converter

Jiarong Liang

AI & ML interests

Recent Activity

Organizations

lllqaq's activity

VisPhyWorld Comparator

VisPhyWorld Comparator

[bot] Conversion to Parquet