Bhavik Chandna

According to our database, Bhavik Chandna authored at least 7 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2026

Survey on LLM Safety: Attacks, Defenses, Alignment, Metrics, and Guardrails.

Pratik Jalan, Vadivel Abishethvarman, Bhavik Chandna, Usman Naseem

Mach. Learn., June, 2026

The Coupling Within: Flow Matching via Distilled Normalizing Flows.

David Berthelot, Tianrong Chen, Jiatao Gu, Marco Cuturi, Laurent Dinh, Bhavik Chandna, Michal Klein, Joshua M. Susskind, Shuangfei Zhai

CoRR, March, 2026

3DSPA: A 3D Semantic Point Autoencoder for Evaluating Video Realism.

Bhavik Chandna, Kelsey R. Allen

CoRR, February, 2026

2025

XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content.

Vadivel Abishethvarman, Bhavik Chandna, Pratik Jalan, Usman Naseem

CoRR, June, 2025

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective.

Zubair Bashir, Bhavik Chandna, Procheta Sen

Trans. Mach. Learn. Res., 2025

ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content.

Bhavik Chandna, Mariam Aboujenane, Usman Naseem

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024

A Counterfactual Explanation Framework for Retrieval Models.

Bhavik Chandna, Procheta Sen

CoRR, 2024