Authors

Changdi Yang

Publications 2

Preprint Open access

BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration

Chence Yang, Ningxi Cheng, Arash Akbari et al. · 2026

Speculative decoding accelerates autoregressive generation by using a lightweight draft to propose multiple tokens for parallel verification. However, existing methods often require an additional draft model or weight representation, introducing non-negligible memory overhead on resource-constrained devices. Self-specu …

Preprint Open access

IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence

Changdi Yang, Fengquan Jiao, Haochih Lin et al. · 2026

We present IronLLM-0.6B, a 654M-parameter language model designed for efficient on-device inference. IronLLM-0.6B combines a hybrid attention architecture with X-MTP, a lightweight shared-KV multi-token prediction design that eliminates per-depth KV-cache replay and employs a lightweight verification head for rollback- …

Co-authors