3 papers
cs.SE2026
Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation
Chengran Yang, Zichao Wei, Heminghao Deng +6
Large Language Model (LLM) based code generation is predominantly formulated as a strictly monotonic process, appending tokens linearly to an immutable prefix. This formulation con…
cs.LG2026
On the Mirage of Long-Range Dependency, with an Application to Integer Multiplication
Zichao Wei
Integer multiplication has long been considered a hard problem for neural networks, with the difficulty widely attributed to the O(n) long-range dependency induced by carry chains.…
cs.CR2025
PATCHEVAL: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities
Zichao Wei, Jun Zeng, Ming Wen +8
Software vulnerabilities are increasing at an alarming rate. However, manual patching is both time-consuming and resource-intensive, while existing automated vulnerability repair (…