Deepti Ghadiyaram PRO

dghadiya's activity

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

submitted a paper to Daily Papers 4 days ago

A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning

Paper • 2604.03995 • Published 8 days ago • 4

upvoted a paper 16 days ago

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents

Paper • 2603.24440 • Published 18 days ago • 96

updated a Space about 2 months ago

Sleeping

Videoeval Humaneval

👁

Rate AI‑generated videos on prompt match and motion quality

upvoted a paper about 2 months ago

DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

Paper • 2602.16968 • Published Feb 19 • 12

updated a dataset about 2 months ago

dghadiya/TAG-Bench-Video

Updated Feb 18 • 1.99k

New activity in dghadiya/TAG-Bench-Video 2 months ago

Remove HF-only videos not present in MOS JSON

#13 opened 2 months ago by

SGTLIM

Remove HF-only videos not present in MOS JSON

#12 opened 2 months ago by

SGTLIM

Add missing videos from MOS JSON (CogVideoX / others)

#11 opened 2 months ago by

SGTLIM

Add CogVideoX/Hunyuan/Opensora_768 UCF videos

#10 opened 2 months ago by

SGTLIM

Add CogVideoX/Hunyuan/Opensora_768 UCF videos

#9 opened 2 months ago by

SGTLIM

Add CogVideoX/Hunyuan/Opensora_768 UCF videos

#8 opened 2 months ago by

SGTLIM

Add CogVideoX/Hunyuan/Opensora_768 UCF videos

#7 opened 2 months ago by

SGTLIM

Add CogVideoX/Hunyuan/Opensora_768 UCF videos

#6 opened 2 months ago by

SGTLIM

New activity in dghadiya/MMA-Bench 4 months ago

Add MMA-Bench dataset (metadata and timestamps)

#2 opened 4 months ago by

dghadiya

Add MMA-Bench dataset (metadata and timestamps)

#4 opened 4 months ago by

dghadiya

Add MMA-Bench dataset (metadata and timestamps)

#5 opened 4 months ago by

dghadiya

Add MMA-Bench dataset (metadata and timestamps)

#1 opened 4 months ago by

dghadiya

published a dataset 4 months ago

dghadiya/MMA-Bench

Viewer • Updated Dec 15, 2025 • 12.9k • 118

upvoted 2 papers 4 months ago

Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs

Paper • 2511.22826 • Published Nov 28, 2025 • 8

Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos

Paper • 2512.01803 • Published Dec 1, 2025 • 5