Bohan Zeng

zbhpku's activity

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

authored 4 papers 11 days ago

Flux-OPD: On-Policy Distillation with Evolving Contexts

Paper • 2607.28022 • Published 18 days ago • 44

DataPrep-Bench: Benchmarking LLMs as Training Data Preparators

Paper • 2607.20465 • Published May 19 • 56

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

Paper • 2607.14202 • Published Jul 15 • 42

CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales

Paper • 2606.21949 • Published Jun 20

upvoted a paper 11 days ago

DataPrep-Bench: Benchmarking LLMs as Training Data Preparators

Paper • 2607.20465 • Published May 19 • 56

upvoted 3 papers 17 days ago

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

Paper • 2607.28509 • Published 18 days ago • 30

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Paper • 2607.28595 • Published 18 days ago • 55

Flux-OPD: On-Policy Distillation with Evolving Contexts

Paper • 2607.28022 • Published 18 days ago • 44

upvoted a paper 26 days ago

DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines

Paper • 2607.16617 • Published about 1 month ago • 143

upvoted 2 papers about 1 month ago

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

Paper • 2607.14202 • Published Jul 15 • 42

MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation

Paper • 2607.14189 • Published Jul 15 • 34

liked a dataset about 2 months ago

KlingTeam/UnityShotsBench

Viewer • Updated Jun 24 • 1.43k • 1.11k • 10

upvoted 2 papers 2 months ago

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

Paper • 2606.13432 • Published Jun 11 • 113

WorldOlympiad: Can Your World Model Survive a Triathlon?

Paper • 2606.11129 • Published Jun 9 • 32

authored 6 papers 2 months ago

Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos

Paper • 2605.18984 • Published May 18 • 22

Towards Next-Generation LLM Training: From the Data-Centric Perspective

Paper • 2603.14712 • Published Mar 16

VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction

Paper • 2605.15186 • Published May 14 • 26

TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos

Paper • 2605.07593 • Published May 8 • 1

LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning

Paper • 2605.22012 • Published May 21 • 46

LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV

Paper • 2605.26244 • Published May 25 • 38