arXiv Machine Learning July 27, 2026 By Run Wang, Chaoyi Zhou, Xi Liu, Yi Zhu, Amir Salarpour, Pedram MohajerAnsari, Zhi-Qi Cheng, Feng Luo, Siyu Huang, Mert D. Pes\'e

Adversarial Prompts for Acceptance Collapse in Speculative Decoding

Read the original on arXiv Machine Learning →

arXiv:2607. 21804v1 Announce Type: cross Abstract: Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv AI

Jun 19

SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling

arXiv:2606. 19755v1 Announce Type: cross Abstract: Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees.

By Haotian Xu, Zeyang Zhang, Linbao Li, Huadi Zheng, Yu Li, Cheng Zhuo

llms benchmarks safety

arXiv AI

Jul 16

UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors

arXiv:2607. 13565v1 Announce Type: cross Abstract: We investigate which language model evasion attacks survive state-of-the-art adversarial fine-tuning, developing strategies that sweep the top 5 positions on the ELOQUENT 2026 Voight-Kampff leaderboard.

By Dima Galat, Marian-Andrei Rizoiu

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jul 31

Beyond the Bidirectional Promise: Re-evaluating the Robustness of Diffusion Language Models

arXiv:2607. 27386v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) offer a compelling alternative to autoregressive (AR) generation by enabling bidirectional context and iterative refinement.

By Saurabh Yadav, Badri Narayana Patro, Vijay Srinivas Agneeswaran

llms diffusion safety

arXiv Machine Learning

Jun 4

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models

arXiv:2606. 04446v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive large language model inference by drafting multiple tokens and verifying them in a single target-model forward pass.

By Liyuan Zhang, Jiarui Zhang, Jinwei Yao, Ran Yan, Yuchen Yang, Jiahao Zhang, Tongkai Yang, Yi Wu, Binhang Yuan

llms diffusion

arXiv Machine Learning

Jun 5

Steering Vectors are an Adversarial Attack Surface

arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.

By Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini, Adrian Robert Minut, Iacopo Masi, Emanuele Rodol\`a

llms fine-tuning multimodal safety

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

Related stories

SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling

UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors

Beyond the Bidirectional Promise: Re-evaluating the Robustness of Diffusion Language Models

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models

Steering Vectors are an Adversarial Attack Surface

SimSD: Simple Speculative Decoding in Diffusion Language Models