← Search

Long (Tony) Lian

2 accepted papers

2026

ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models

ICML 2026oral

Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but their inherently sequential decoding incurs substantial latency, motivating parallelization of the generation process. However, existing parallel reasoning approaches suffer from …

Cited by 0SourceScholar
2026

V1: Unifying Generation and Self-Verification for Parallel Reasoners

ICML 2026poster

Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, for example by independently sampling and aggregating multiple solutions, results in significantly better task outcomes. However, a critical bottleneck is _verification_: sampling is only effective if correct…

Cited by 0SourceScholar