18 papers · 1 filter
Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation
Zekai Li, Ji Liu, Yiqing Huang +3
Diffusion-based large language models (dLLMs) support parallel text generation via iterative denoising, yet inference remains latency-heavy because many steps are spent on redundan…
PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
Zihao An, Taichi Liu, Ziqiong Liu +3
Speculative decoding accelerates Large Language Models (LLMs) inference by using a lightweight draft model to propose candidate tokens that are verified in parallel by the target m…
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
Jinze Li, Yixing Xu, Guanchen Li +6
Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive generation. Speculative Decoding (SP…
AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection
Pretam Ray, Pratik Prabhanjan Brahma, Zicheng Liu +1
Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large language models (LLMs) during inference.…
CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models
Yihao Liang, Ze Wang, Hao Chen +7
Autoregressive large language models achieve strong results on many benchmarks, but decoding remains fundamentally latency-limited by sequential dependence on previously generated…
Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates
Yixing Xu, Chao Li, Xuanwu Yin +4
Low-rank adaptation (LoRA) is one of the most popular methods among parameter-efficient fine-tuning (PEFT) methods to adapt pre-trained large language models (LLMs) to specific dow…