Jinpeng Lu

JinPLU's activity

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

updated a dataset 6 days ago

WRBench/wrbench-human-annotations

Viewer • Updated 6 days ago • 8.12k • 619

upvoted a paper 12 days ago

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published 16 days ago • 84

updated a Space 16 days ago

Running

2

WRBench Leaderboard

🎬

2

Diagnostic D1-D6 leaderboard for world models

updated 3 datasets 16 days ago

WRBench/wrbench-results

Viewer • Updated 16 days ago • 26 • 175

WRBench/wrbench-videos

Viewer • Updated 16 days ago • 11.2k • 7.37k

WRBench/wrbench-natural25

Viewer • Updated 16 days ago • 1.4k • 420

New activity in WRBench/wrbench-natural25 17 days ago

Add Parquet Viewer views for the paper release

1

#3 opened 17 days ago by

JinPLU

Publish paper_main_20260608 reproducibility metadata

1

#2 opened 17 days ago by

JinPLU

New activity in WRBench/wrbench-videos 17 days ago

Publish paper_main_20260608 reproducibility metadata

1

#3 opened 17 days ago by

JinPLU

upvoted a paper 20 days ago

Bernini: Latent Semantic Planning for Video Diffusion

Paper • 2605.22344 • Published May 21 • 20

updated a Space 21 days ago

Running

WRBench

🎥

Persistent-state world model benchmark

upvoted a paper 21 days ago

CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

Paper • 2605.12496 • Published May 12 • 31

upvoted a collection 29 days ago

WRBench: Current World Models Lack a Persistent State Core

Collection

WRBench public release: paper, prompts, videos, scores, human labels, and leaderboard. • 6 items • Updated 21 days ago • 3

upvoted 2 papers about 1 month ago

Memento: Reconstruct to Remember for Consistent Long Video Generation

Paper • 2606.14667 • Published Jun 12 • 18

VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing

Paper • 2605.30117 • Published May 28 • 2

authored 4 papers about 1 month ago

Does DINOv3 Set a New Medical Vision Standard?

Paper • 2509.06467 • Published Sep 8, 2025 • 39

Pelican-Unified 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action

Paper • 2605.15153 • Published May 14 • 1

VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing

Paper • 2605.30117 • Published May 28 • 2

Current World Models Lack a Persistent State Core

Paper • 2606.20545 • Published Jun 18 • 17

New activity in WRBench/wrbench-videos about 1 month ago

Add model intake diagnostic evidence videos

#1 opened about 1 month ago by

JinPLU