Scholar
Anamika Lochab
Google Scholar ID: GsQz5PkAAAAJ
Purdue University
Artificial Intelligence
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
20
H-index
1
i10-index
1
Publications
4
Co-authors
0
Contact
Email
alochab@purdue.edu
GitHub
Open ↗
LinkedIn
Open ↗
Publications
3 items
VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
2025
Cited
0
VERA: Variational Inference Framework for Jailbreaking Large Language Models
2025
Cited
0
Energy-Based Reward Models for Robust Language Model Alignment
2025
Cited
0
Resume (English only)
Academic Achievements
Paper 'VERA: Variational Inference Framework for Jailbreaking Large Language Models' accepted at NeurIPS 2025.
Paper 'Energy-Based Reward Models for Robust Language Model Alignment' published at COLM 2025.
Paper 'Cascade Reward Sampling for Efficient Decoding-Time Alignment' published at COLM 2025.
NeurIPS Scholar/Travel Award 2025.
NSF ACCESS Discover Project Award (2025–2026).
COLM Travel Award 2025.
Outstanding Project Award, Rutgers University (2024).
Gold Medallist, VIT Bhopal (2022).
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up