Presenting 'Balancing Act: Distribution-Guided Debiasing in Diffusion Models' poster in 4E-182 at #CVPR2026 now. Please visit our poster to know more!

Had a great time presenting our papers today at #CVPR2026 !

We introduce Situated Instruction Following (SIF), to appear in ECCV 2024! There is inherent underspecification in instructions when humans act as they speak. SIF is addresses these dynamic, temporally evolving intent of instructions in the context of physical human actions.(1/7)

Our CVPR'24 work - "Balancing Act: Distribution-Guided Debiasing in Diffusion Models" is covered by Times of India. Congrats to the team! Rishubh Parihar, Oops, Abhipsa Basu, Saswat Mallick, Jogendra Nath Kundu and Venkatesh Babu TOI web login: timesofindia.indiatimes.com/city/bengaluru… #AI

IKDD congratulates Sravanti Addepalli IISc Bangalore  for enhancing the robustness of Deep Neural Networks against adversarial attacks and distribution shifts while addressing practical deployment challenges. Preethi Jyothi Manish Gupta Amith Singhee

🎉 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

🤖 Some company just released a new set of open-weight LLMs well-suited for your production environment. However, you suspect that the models might be trained with backdoors or other hidden malicious behaviors. Is it still possible to deploy these models worry-free? (1/7)