Tech Xplore

Making LLMs faster and more efficient across multiple languages

Large language models (LLMs), which are the artificial intelligence (AI) systems behind modern chatbots, translation tools, ...
EDN

The hidden bottleneck in LLM inference and the impact on MLPerf benchmarking

Here is how the prefill versus generation split exposes GPU structural inefficiencies in AI processor designs.
Semiconductor Engineering

The Edge LLM Offload Story

Developers and system architects today face a growing demand to enable large language model variants on device. They are facing pressure to support transformer-capable models on constrained devices to ...
Edhat

Yuheng Bu seeks a better way to ensure the trustworthiness of AI-generated text

UC Santa Barbara’s Robert Mehrabian College of Engineering, Yuheng Bu, assistant professor in the Computer Science Department, has received a prestigious Early CAREER Award from the National Science F ...
Ars Technica

Google’s Gemma 4 AI models get 3x speed boost by predicting future tokens

Google launched its Gemma 4 open models this spring, promising a new level of power and performance for local AI. Google’s take on edge AI could be getting even faster already with the release of ...
IEEE

Low Bit-Width LLM Acceleration via Symmetric Lookup Format and Compute-in-Decoding Paradigm

Abstract: Recent large language models (LLMs), driven by the scaling law, have demonstrated remarkable performance in various machine learning tasks by significantly increasing model size. However, ...
Semiconductor Engineering

Microarchitecture Tailored to 3D-Stacked Near-Memory Processing LLM Decoding (U. of Edinburgh, Peking U., Cambridge et al.)

A new technical paper, “Rethinking Compute Substrates for 3D-Stacked Near-Memory LLM Decoding: Microarchitecture-Scheduling Co-Design,” was published by researchers at University of Edinburgh, Peking ...
VentureBeat

Researchers baked 3x inference speedups directly into LLM weights — without speculative decoding

As agentic AI workflows multiply the cost and latency of long reasoning chains, a team from the University of Maryland, Lawrence Livermore National Labs, Columbia University and TogetherAI has found a ...
The New York Times

Decoding the A.I. Beliefs of Anthropic and Its C.E.O., Dario Amodei

The company is at odds with the Pentagon over how its A.I. will be used. The conflict has its roots in the foundational plan for Anthropic. By Cade Metz Reporting from San Francisco The Defense ...
GitHub

Steganographic data encoding in natural language using LLM logit-rank steering

subtext-codec is a proof-of-concept codec that hides arbitrary binary data inside seemingly normal LLM-generated text. It steers a language model's next-token choices using the rank of each token in ...