arXiv Computation and Language August 27, 2026 By Ming Ma, Bowen Zheng, Zhongqiao Lin, Tianming Yang

SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token

Read the original on arXiv Computation and Language →

The Flow has not summarised this story yet — read it at arXiv Computation and Language.

llms

arXiv Machine Learning

Jul 13

Accelerating Large Language Model Inference with Self-Supervised Early Exits

arXiv:2407. 21082v3 Announce Type: replace-cross Abstract: This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers.

By Florian Valade

llms benchmarks

arXiv AI

Jun 16

Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens

arXiv:2606. 16847v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) offer a promising avenue for parallel generation but face a trade-off between decoding speed and quality.

By Yizhen Yao, Qinglin Zhu, Runcong Zhao, Xiangxiang Dai, Yanzheng Xiang, Yulan He, Lin Gui

llms rag diffusion efficiency benchmarks

arXiv AI

Jun 2

SimSD: Simple Speculative Decoding in Diffusion Language Models

arXiv:2606. 02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding.

By Junxia Cui, Haotian Ye, Runchu Tian, Hongcan Guo, Jinya Jiang, Haoru Li, Chaojie Ren, Yiming Huang, Kaijie Zhu, Zhongkai Yu, Kun Zhou, Jingbo Shang

llms diffusion efficiency benchmarks

arXiv Machine Learning

Jul 3

PARTREP: Learning What to Repeat for Decoder-only LLMs

arXiv:2607. 01792v1 Announce Type: cross Abstract: While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in contextual grounding than earlier ones.

By Andikawati P Widjaja, Yongjun Kim, Hyounghun Kim, Jaeho Lee

llms efficiency benchmarks

arXiv AI

Jun 3

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

arXiv:2604. 18995v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction.

By Zhenbang Du, Kejing Xia, Xinrui Zhong, Yonggan Fu, Nicolai Oswald, Binfei Ji, Brucek Khailany, Pavlo Molchanov, Yingyan Lin

llms diffusion fine-tuning efficiency

arXiv AI

Jul 21

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage

arXiv:2601. 03043v4 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency.

By Junhao Hu, Fangze Li, Mingtao Xu, Feifan Meng, Shiju Zhao, Tiancheng Hu, Ting Peng, Anmin Liu, Wenrui Huang, Chenxu Liu, Ziyue Hua, Tao Xie

llms benchmarks

One email a morning, machine-written

Related stories

Accelerating Large Language Model Inference with Self-Supervised Early Exits

Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens

SimSD: Simple Speculative Decoding in Diffusion Language Models

PARTREP: Learning What to Repeat for Decoder-only LLMs

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage