DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
Paper • 2607.16617 • Published • 137
Bohan Zeng
zbhpku
AI & ML interests
None yet
Recent Activity
Organizations
None yet
upvoted a paper 8 days ago
upvoted 2
papers 13 days ago
liked a
dataset about 1 month ago
upvoted 2
papers about 2 months ago
authored 7
papers about 2 months ago
Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos
Paper • 2605.18984 • Published • 22
Towards Next-Generation LLM Training: From the Data-Centric Perspective
Paper • 2603.14712 • Published
VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction
Paper • 2605.15186 • Published • 26
TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos
Paper • 2605.07593 • Published • 1
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
Paper • 2605.22012 • Published • 46
LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV
Paper • 2605.26244 • Published • 38
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks
Paper • 2606.09669 • Published • 47
upvoted 3
papers about 2 months ago
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks
Paper • 2606.09669 • Published • 47
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
Paper • 2606.02564 • Published • 29
DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory
Paper • 2605.31336 • Published • 12
upvoted 2
papers 2 months ago
submitted a
paper to Daily Papers 2 months ago
upvoted a paper 2 months ago