Foundational research in large language models, multi-step reasoning, and intelligent agents driving the next generation of AI systems.
We focus on making large language models more efficient, accurate, and deployable. Our research spans quantization, distillation, and hardware-aware optimization techniques.
Reduced latency through quantization and pruning
Knowledge distillation for edge deployment
Optimized for specific compute targets
Building intelligent agents capable of multi-step reasoning, tool use, and autonomous task completion. Our agents combine planning, memory, and execution capabilities.
Complex task decomposition and execution
API calls, code execution, and retrieval
Long-term context retention and recall
Our research spans multiple domains within AI, each contributing to more capable and reliable systems.
Symbolic computation integration and proof generation for verifiable AI outputs.
Bug detection, automated repair, test generation, and code synthesis.
Comprehensive benchmarks and protocols for measuring AI system performance.
We're open to research collaborations with academic institutions, industry partners, and government organizations.