Skip to content

TESSERA: Programming Petabytes of Earth Observations using Foundation Models by Prof. Anil Madhavapeddy

Bharti 501 IIT Campus, Hauz Khas, New Delhi

Venue. Bharti 501 Abstract. We present TESSERA, a pixel-wise foundation model for multi-modal (Sentinel-1/2) earth observation time series that learns robust, label-efficient embeddings.  Our goal with TESSERA is to make manipulating… Read More »TESSERA: Programming Petabytes of Earth Observations using Foundation Models by Prof. Anil Madhavapeddy

Neural Circuit Discovery via Representation and Dynamics by Savik Kinger

SIT 113 Amar Nath and Shashi Khosla School of Information Technology, Indian Institute of Technology, Delhi, Hauz Khas, New Delhi, Delhi, India

Abstract: Neuroscience and AI share a bottleneck: while one can build (artificial) or record (biological) complex networks, we struggle to explain their functional circuitry; i.e., how they compute. In this… Read More »Neural Circuit Discovery via Representation and Dynamics by Savik Kinger

Genteel-Negotiator: LLM-enhanced mixture-of-expert-based reinforcement learning approach for polite negotiation dialogue by Dr. Mauajama Firdaus

SIT 001 Amar Nath and Shashi Khosla School of Information Technology, IIT Delhi, Hauz Khas, New Delhi 110016, India, Delhi, Delhi, India

Venue: SIT001 Abstract : Developing intelligent negotiation dialogue systems that promote fair and sustainable outcomes is crucial for advancing automated negotiation for social good. Since effective negotiation requires balancing cooperation and… Read More »Genteel-Negotiator: LLM-enhanced mixture-of-expert-based reinforcement learning approach for polite negotiation dialogue by Dr. Mauajama Firdaus

Machine Learning under Adversaries: How Structure in Data Helps by Ambar Pal

SIT 001 Amar Nath and Shashi Khosla School of Information Technology, IIT Delhi, Hauz Khas, New Delhi 110016, India, Delhi, Delhi, India

Venue: SIT001 Abstract: This talk overviews recent results in the theoretical foundations of adversarially robust machine learning. Modern ML classifiers can fail spectacularly when subject to specially crafted input-perturbations, called… Read More »Machine Learning under Adversaries: How Structure in Data Helps by Ambar Pal