💫Congrats Jogendra Nath Kundu 🎉🎉, for receiving the prestigious ACM India 2023 Doctoral Dissertation Award - Honorable Mention!! awards.acm.org/india-doctoral… ACM India IISc Computational and Data Sciences IISc Bangalore

The list of #ECCV2024 Outstanding Reviewers! Thank you for your service 🫡 eccv.ecva.net/Conferences/20…

Honored to be recognized as an Outstanding Reviewer for ECCV 2024 European Conference on Computer Vision #ECCV2026 Also will be presenting our paper on Interpretability-Guided Adversarial Robustness at ECCV this year (poster session 4 on Oct 2nd, 4:30 pm to 6:30 pm) arxiv.org/abs/2409.15190

Excited to share our work at #EMNLP2024! 🎉 If you're interested in adversarial robustness or robustness in general, I'd love to connect and discuss :) Unfortunately, I couldn't attend in person due to visa issues, but I’m available for online chats! 📍 Today 17:45 to 18:45 EST

🎉 Congratulations to Harsh Rangwani on successfully defending his PhD thesis today! We're incredibly proud of your hard work, dedication, and perseverance. Wishing you great success as you step into this new chapter as Dr. Harsh! 🚀 #PhDDefense IISc Computational and Data Sciences IISc Bangalore

Interpreting Neurons in Deep Vision Networks with Language Models Nicholas Bai, Rahul Ajay Iyer, Tuomas Oikarinen, Akshay R. Kulkarni, Tsui-Wei Weng. Action editor: Antoine Ledent. openreview.net/forum?id=x1dXv… #neuron #neurons #deep

A 🧵 on our recent work at #ICRA25. PIP-Loco: A Proprioceptive Infinite Horizon Planning Framework for Quadrupedal Robot Locomotion (stochlab.com/PIP-Loco)

⚡ Making Deep Generative Models Inherently Interpretable – Catch us at #CVPR25 this week! ⚡ We’re excited to present our paper, Interpretable Generative Models through Post-hoc Concept Bottlenecks, at #CVPR2025 2025 this week! 🚀Project site: lilywenglab.github.io/posthoc-genera…

Are Firewalls All You Need, or Stronger Benchmarks? Benchmarking is critical for understanding and comparing the security of tool-calling agents. As attacks evolve and defenses adapt, researchers need consistent, realistic, and reproducible evaluation frameworks to identify true

🚨 New Paper Alert! 🚀 Excited to introduce CAVE: A benchmark for detecting and explaining commonsense anomalies in real-world visual environments! Accepted at #EMNLP2025 Main Conference! 🎉 📍Join us at our poster on Nov 5, 16:30-18:00 in Hall C.

Excited to share that I'll be at #NeurIPS2025 from Dec 2-7, presenting two of my works 🚀 1. LLM Agent Safety Against Prompt Injections 2. Anomaly Detection Using VLMs I’m looking for PhD positions starting Fall 2026. Happy to connect, feel free to DM :) Poster details in 🧵