Yonatan Bisk

Need my Bio for something

Bio:
Yonatan Bisk is an assistant professor of computer science at Carnegie Mellon University – Language Technologies Institute and Robotics Institute (courtesy). He received his PhD from the University of Illinois at Urbana-Champaign working on unsupervised Bayesian models of linguistic syntax.

He runs the CLAW lab, Connecting Language to Action and the World. His group works on grounded and embodied language and communication, placing perception and interaction as central to how language is learned and understood. He has held appointments at USC's ISI (working on grounding), the University of Washington (for commonsense research), Microsoft Research (for vision+language), and Meta Inc (for Embodied AI).

Website:
http://www.yonatanbisk.com

Photo URL:
https://talkingtorobots.com/images/YonatanBisk_400.jpg

Applying to LTI vs RI vs MLD: The short answer is you should apply to the department whose curriculum aligns most closely with your educational and research goals. The department does not restrict who can serve as your advisor, but it does change when we get access to the applicant pool a little to add comments and whether my name is in the default drop down for visit days. You can select me during visit days regardless.

- DiffusionPID: Interpreting Diffusion via Partial Information Decomposition

- Tools Fail: Detecting Silent Errors in Faulty Tools

- Gradient Localization Improves Lifelong Pretraining of Language Models

- How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models

- ANAVI: Audio Noise Awareness by Visual Interaction

- AgentKit: Flow Engineering with Graphs, not Coding

- Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers

- OpenEQA: Embodied Question Answering in the Era of Foundation Models

- SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
- WebArena: A Realistic Web Environment for Building Autonomous Agents

- MOSAIC: Learning Unified Multi-Sensory Object Property Representations for Robot Perception

- SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning
- SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs

- HomeRobot: Open-Vocabulary Mobile Manipulation
- Spatial-Language Attention Policies for Efficient Robot Learning