Jinhe Bi

Jinhe's activity

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

upvoted a paper 1 day ago

OPD-V: Visual On-Policy Self-Distillation with Modality Balance

Paper • 2608.05131 • Published 3 days ago • 8

upvoted a paper 2 days ago

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning

Paper • 2608.03972 • Published 4 days ago • 3

upvoted a paper 6 months ago

How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning

Paper • 2602.10622 • Published Feb 11 • 28

upvoted 2 papers 10 months ago

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints

Paper • 2510.19316 • Published Oct 22, 2025 • 12

Reinforcement Mid-Training

Paper • 2509.24375 • Published Sep 29, 2025 • 10

upvoted a paper about 1 year ago

Backdoor Cleaning without External Guidance in MLLM Fine-tuning

Paper • 2505.16916 • Published May 22, 2025 • 17