Guanxi Lu — accepted AI-conference papers

2026

Semantic-Aware Diffusion LLM Inference With Adaptive Block Size

Guanxi Lu, Hao Mark Chen, Yuto Karashima, Zhican Wang, Daichi Fujiki, Hongxiang Fan

ICLR 2026poster

Diffusion-based large language models (dLLMs) are gaining attention for their inherent capacity for parallel decoding, offering a compelling alternative to autoregressive LLMs. Among various decoding strategies, blockwise semi-autoregressive (semi-AR) approaches are widely adopted due to their natur…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling

Hao Mark Chen, Guanxi Lu, Yasuyuki Okoshi, Zhiwen Mo, Masato Motomura, Hongxiang Fan

NeurIPS 2025poster

Test-time scaling (TTS) has proven effective in enhancing the reasoning capabilities of large language models (LLMs). Verification plays a key role in TTS, simultaneously influencing (1) reasoning performance and (2) compute efficiency, due to the quality and computational cost of verification. In t…

Cited by 0 Source ↗Scholar ↗