Junhan ZHU

Alrightlone's activity

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

upvoted a paper 5 days ago

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding

Paper • 2510.23479 • Published 7 days ago • 14

upvoted 2 papers 11 days ago

VChain: Chain-of-Visual-Thought for Reasoning in Video Generation

Paper • 2510.05094 • Published 28 days ago • 36

3D and 4D World Modeling: A Survey

Paper • 2509.07996 • Published Sep 4 • 57

upvoted a paper 20 days ago

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression

Paper • 2510.08525 • Published 25 days ago • 22

upvoted 2 papers 25 days ago

TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

Paper • 2507.21584 • Published Jul 29 • 10

OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot

Paper • 2510.06751 • Published 26 days ago • 21

upvoted a paper about 1 month ago

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Paper • 2510.02240 • Published Oct 2 • 17

upvoted a collection about 1 month ago

ReasonMap

Collection

A fine-grained visual reasoning benchmark (We show more question types in the extension dataset.) • 3 items • Updated Oct 1 • 8

upvoted a paper 3 months ago

HoliTom: Holistic Token Merging for Fast Video Large Language Models

Paper • 2505.21334 • Published May 27 • 21