Tianhe Wu
TianheWu
AI & ML interests
Generative Modeling, VLM/LLM
Recent Activity
authored a paper 6 days ago
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO upvoted a paper 6 days ago
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO upvoted a paper 12 days ago
On the Geometry of On-Policy DistillationOrganizations
-
VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
Paper • 2505.14460 • Published • 34 -
A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment
Paper • 2403.10854 • Published • 1 -
TianheWu/VisualQuality-R1-7B-preview
Reinforcement Learning • 8B • Updated • 307 • 7 -
TianheWu/VisualQuality-R1-7B
Reinforcement Learning • 8B • Updated • 11.7k • 13
-
VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
Paper • 2505.14460 • Published • 34 -
A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment
Paper • 2403.10854 • Published • 1 -
TianheWu/VisualQuality-R1-7B-preview
Reinforcement Learning • 8B • Updated • 307 • 7 -
TianheWu/VisualQuality-R1-7B
Reinforcement Learning • 8B • Updated • 11.7k • 13
models 22
TianheWu/dpdmd
Text-to-Image • Updated • 1
TianheWu/VisualQuality-R1-7B-preview
Reinforcement Learning • 8B • Updated • 307 • 7
TianheWu/VisualQuality-R1-7B
Reinforcement Learning • 8B • Updated • 11.7k • 13
TianheWu/extract_prin_for_judgment_8_grm_instruct
Updated • 1
TianheWu/extract_prin_for_judgment_16_grm_instruct
Updated • 1
TianheWu/extract_balance_dir_par_seq_r1_grm_base
Updated • 1
TianheWu/extract_reasoning_principle_judgment_8_base
Updated • 2
TianheWu/extract_reasoning_principle_judgment_16_base
Updated • 1
TianheWu/extract_reasoning_principle_judgment_8
Updated • 2
TianheWu/extract_reasoning_principle_judgment_16
Updated • 3
datasets 0
None public yet