2 papers
cs.SE2026
Discovering 100+ Compiler Defects in 72 Hours via LLM-Driven Semantic Logic Recomposition
Xingbang He, Yuanwei Chen, Hao Wu +9
Compilers constitute the foundational root-of-trust in software supply chains; however, their immense complexity inevitably conceals critical defects. Recent research has attempted…
cs.LG2025
SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification
Zhendong Tan, Xingjun Zhang, Chaoyi Hu +2
Growing demands from tasks like code generation, deep reasoning, and long-document understanding have made long-context generation a crucial capability for large language models (L…