Kumar Krishna Agrawal

I am a final year PhD student at UC Berkeley, where I work at the intersection of AI, systems, and computer vision. I am affiliated with BAIR and UCSF, and am incredibly fortunate to be co-advised by Adam Yala and Trevor Darrell. I also work closely with Sky Computing Lab.

My research is dedicated to building algorithms and systems for human-centric AI.

Advancing Capabilities: How do we build machines that assist us to better perceive, understand, and reason about the real world?

(gansynth, atlas)

Algorithms: How do we design learning algorithms that are data/compute efficient?

(tracing representation geometry, , α-ReQ, discriminator actor-critic. discrete flows)

Systems: How do we enable efficient inference for long-context, multimodal models?

(vAttention, Octopus, Pangolin)

Previously

Google Brain – robotics, generative models, program synthesis
IIT Kharagpur – mathematics and computer science
MILA – with Yoshua Bengio