Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
Haoyun Jiang, Junqi He, Feng Hong +8
Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and respo…
cs.LG2025
Rapid morphology characterization of two-dimensional TMDs and lateral heterostructures based on deep learning
Junqi He, Yujie Zhang, Jialu Wang +6
Two-dimensional (2D) materials and heterostructures exhibit unique physical properties, necessitating efficient and accurate characterization methods. Leveraging advancements in ar…