Agora | Research Hub

Citations & Impact

All-time

Citations

8,237

H-index

39

i10-index

102

Publications

20

Co-authors

21

list available

Contact

CVOpen ↗TwitterOpen ↗GitHubOpen ↗

Publications

44 items

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning

2026

Cited

0

Why Instruction-Based Unlearning Fails in Diffusion Models?

2026

Cited

0

TDMM-LM: Bridging Facial Understanding and Animation via Language Models

2026

Cited

0

Training Large Reasoning Models Efficiently via Progressive Thought Encoding

2026

Cited

0

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks

2026

Cited

1

Omni-Judge: Can Omni-LLMs Serve as Human-Aligned Judges for Text-Conditioned Audio-Video Generation?

2026

Cited

0

Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling

2026

Cited

0

Semantic visually-guided acoustic highlighting with large vision-language models

2026

Cited

0

Resume (English only)

Academic Achievements

Numerous papers accepted at top-tier venues including CVPR, ICCV, ECCV, NeurIPS, AAAI, ICLR, ACM MM, SIGGRAPH Asia, EMNLP, and NAACL
ACC V 2024 Best Paper Award Honorable Mention
Outstanding Speaker Award at the 1st Physical Retail AI Workshop (WACV 2024)
Led or co-led major grants: $5.9M DARPA PTG, $2.9M NIH R01 (x2), $375k NSF CDS&E, $574k DOE NNSA, $400k Meta grant, etc.
Received research gifts from Sony, Cisco, Adobe, Corning, and others
Mentored multiple Ph.D. graduates now at Amazon AWS, Adobe Research, UT Dallas, Oppo US Research, etc.

Co-authors

21 total