Search papers, labs, and topics across Lattice.
Affiliation:
6
2
10
49
A critical-path-aware performance analysis methodology that automatically discovers recurring performance patterns by synthesizing static code features, dynamic execution traces, and kernel-level resource data, finding 13 distinct performance archetypes that appear consistently across different applications, independent of their domain or implementation.
vLLM emerges as the leading framework for LLM serving, but developers are missing out on the advantages of multi-framework integration.
Rust developers can slash the noise in static analysis alerts by over 50% using an RL agent that learns to suppress false positives, outperforming even LLM-based methods.
CoT's code generation prowess isn't a sure thing: its robustness crumbles when input tweaks destabilize key "structural anchors" in the reasoning process.
Forget monolithic LLMs for requirements engineering: QUARE's multi-agent negotiation framework achieves 105% better compliance by explicitly surfacing and resolving inter-quality conflicts.
LLM-powered program repair tools can memorize bug fixes, but struggle with minor syntactic changes and applying fixes in real-world projects, revealing a critical gap in their reasoning abilities.
