Communications of the ACM

Copiloting the Copilots for Automated Program Repair

During automated (APR), it can be challeng\x02ing to synthesize correct patches for real-world systems in general-purpose ...

Generative AI for polymer design passes lab tests with a new dielectric material

The words on this page mean something because they are assembled in a particular order and follow the complex rules of ...
IEEE

Bridging Models and Language: An Encoder-Decoder Approach for Automated Architectural Documentation with LLMs

Abstract: In modern software development, maintaining consistency between architectural documentation and implementation remains a significant challenge. This research explores how large language ...
InfoQ

Google Researchers Propose Bayesian Teaching Method for Large Language Models

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Soroosh Khodami discusses why we aren't ready ...
InfoWorld

Multi-token prediction technique triples LLM inference speed without auxiliary draft models

With reported 3x speed gains and limited degradation in output quality, the method targets one of the biggest pain points in production AI systems: latency at scale. High inference latency and ...
VentureBeat

Nvidia’s new technique cuts LLM reasoning costs by 8x without losing accuracy

Researchers at Nvidia have developed a technique that can reduce the memory costs of large language model reasoning by up to eight times. Their technique, called dynamic memory sparsification (DMS), ...
Inc

Are LTMs the Next LLMs? This New Type of AI Can Do What Large-Language Models Can’t

Large-language models (LLMs) have taken the world by storm, but they’re only one type of underlying AI model. An under-the-radar company, Fundamental, is set to bring a new type of enterprise AI model ...
TechCrunch

Tiny startup Arcee AI built a 400B-parameter open source LLM from scratch to best Meta’s Llama

Many in the industry think the winners of the AI model market have already been decided: Big Tech will own it (Google, Meta, Microsoft, a bit of Amazon) along with their model makers of choice, ...
Bleeping Computer

Hackers hijack exposed LLM endpoints in Bizarre Bazaar operation

A malicious campaign is actively targeting exposed LLM (Large Language Model) service endpoints to commercialize unauthorized access to AI infrastructure. Over a period of 40 days, researchers at ...
Semiconductor Engineering

Ultra-low-bit LLM Inference Allows AI-PC CPUs And Discrete Client GPUs To Approach High-end GPU-Level (Intel)

A new technical paper titled “Pushing the Envelope of LLM Inference on AI-PC and Intel GPUs” was published by researcher at Intel. “The advent of ultra-low-bit LLM models (1/1.58/2-bit), which match ...