Swetha Sirnam

PhD student@University of Central Florida·美国·OpenReview

研究方向

Object Segmentation · Object tracking · Complex activity · Scene understanding · Action detection · Action recognition · Video understanding · Deep learning · Multi-Modal Learning · MLLMs · Preference Optimization · Video LLMs

5.3

The Telephone Game: Evaluating Semantic Drift in Unified Models

ICLR 2026Rejected

三作

4.7

StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales

ICLR 2026Rejected

三作

4.0

Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety

合作者 (15)

Jeffrey A Chan Santiago

1 篇

Joseph Fioresi

1 篇

Swetha Sirnam

The Telephone Game: Evaluating Semantic Drift in Unified Models

StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales

Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety

ImplicitQA: Going beyond frames towards Implicit Video Reasoning

GeoTimeCLIP: Unveiling the When and Where of Images

StretchySnake: Flexible VideoMamba for Short and Long-Form Action Recognition