Paper Trail
Search
Search
Dark mode
Light mode
Explorer
Tag: shanghai-ai-lab
12 items with this tag.
Mar 19, 2026
Unified Personalized Reward Model for Vision Generation
paper
reward-model
fudan
shanghai-ai-lab
modality/image
modality/video
Mar 18, 2026
VBench: Comprehensive Benchmark Suite for Video Generative Models
paper
reward-model
ntu
shanghai-ai-lab
cuhk
nju
modality/video
Mar 18, 2026
Flow-GRPO: Training Flow Matching Models via Online RL
paper
image-generation-posttrain
kuaishou
cuhk
shanghai-ai-lab
modality/image
modality/text
Mar 18, 2026
T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
paper
image-generation-posttrain
cuhk
shanghai-ai-lab
modality/image
modality/text
Mar 18, 2026
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
paper
reward-model
shanghai-ai-lab
modality/image
modality/video
modality/text
Mar 18, 2026
Process Reinforcement through Implicit Rewards
paper
reward-model
tsinghua
shanghai-ai-lab
modality/text
Mar 18, 2026
Unified Reward Model for Multimodal Understanding and Generation
paper
reward-model
fudan
shanghai-ai-lab
modality/image
modality/video
Mar 18, 2026
VisualPRM: An Effective Process Reward Model for Multimodal Reasoning
paper
reward-model
shanghai-ai-lab
modality/image
modality/text
Mar 18, 2026
Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
paper
reward-model
fudan
shanghai-ai-lab
tencent
modality/image
modality/video
Mar 18, 2026
HPSv3: Towards Wide-Spectrum Human Preference Score
paper
reward-model
cuhk
shanghai-ai-lab
modality/image
Mar 18, 2026
ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning
paper
reward-model
shanghai-ai-lab
fudan
modality/image
modality/text
Mar 18, 2026
Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation
paper
reward-model
sjtu
shanghai-ai-lab
modality/image
modality/text