Search papers, labs, and topics across Lattice.
UC San Diego
3
0
4
3
Coding agents can now access repository context 8.7x faster, dramatically improving efficiency in navigating evolving codebases.
Current LLM memory systems falter when faced with the continuous, machine-generated interaction streams typical of real-world agentic applications, highlighting a critical need for causality-aware and tool-augmented memory architectures.
LLMs still have a long way to go in AI-aided chip design, with even the best models achieving surprisingly low scores on the new ChipBench benchmark for Verilog generation and reference model creation.
