activity
20242026
most citedGet More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference

1 citations · 1 across the 19 of their papers we have counts for

collaborators
Showing 2025 · cs.CRShow all

1 paper · 2 filters

cs.CR2025

When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?

Yibo Peng, James Song, Lei Li +6

Code agents are increasingly trusted to autonomously fix bugs on platforms such as GitHub, yet their security evaluation focuses almost exclusively on functional correctness. In th…