works on

From the 1 of 9 linked papers with an AI index.

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?

Tianyu Liu, Yuhao Shen, Xinyi Hu +8

Speculative decoding accelerates LLM inference, but SOTA hidden-state-based drafters suffer from long-range decay: draft accuracy degrades as the speculative step increases. Existi…

cs.CL2026

Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects

Jun Zhang, Yicheng Ji, Feiyang Ren +7

Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token d…

cs.CL2026

On the Step Length Confounding in LLM Reasoning Data Selection

Bing Wang, Rui Miao, Chen Shen +7

Large reasoning models have recently demonstrated strong performance on complex tasks that require long chain-of-thought reasoning, through supervised fine-tuning on large-scale an…

cs.CL2026

See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs

Yicheng Ji, Jun Zhang, Jinpeng Chen +4

Video Large Language Models (Video-LLMs) excel in video understanding but suffer from high inference latency during autoregressive generation. Speculative Decoding (SD) mitigates t…

cs.CL2026

KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization

Mingbo Song, Heming Xia, Jun Zhang +4

Speculative Decoding (SD) has emerged as a widely used paradigm to accelerate the inference of large language models (LLMs) without compromising generation quality. It works by eff…

cs.CL2025

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

Heming Xia, Yongqi Li, Jun Zhang +2

Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality. It works by first employing a compact model to draft multi…