← Search

Qiujiang Chen

2 accepted papers

2026

ATTS: Asynchronous Test-Time Scaling via Conformal Prediction

ICLR 2026poster

Large language models (LLMs) benefit from test-time scaling but are often hampered by high inference latency. Speculative decoding is a natural way to accelerate the scaling process; however, scaling along both the parallel and sequential dimensions poses significant challenges, including substantia…

Cited by 0SourcecodeScholar
2026

SWINGARENA: Adversarial Programming Arena for Long-context GitHub Issue Solving

ICLR 2026oral

We present \textsc{SwingArena}, a adversarial evaluation framework for Large Language Models (LLMs) that closely mirrors real-world software development workflows. Unlike traditional static benchmarks, \textsc{SwingArena} models the collaborative process of software iteration by pairing LLMs as \tex…

Cited by 0SourcecodeScholar