IEEE

Bit-serial Acceleration of LLM Inference with Mixture-of-Datatype Quantization

Abstract: Large language models (LLMs) have achieved significant breakthroughs on machine learning tasks. Yet the substantial memory footprint of LLMs significantly hinders their wide deployment. In ...
Microsoft

TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge

Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference deployment without ...
MIT Technology Review

OpenAI has trained its LLM to confess to bad behavior

Large language models often lie and cheat. We can’t stop that—but we can make them own up. OpenAI is testing another new way to expose the complicated processes at work inside large language models.
Morningstar

Redrob Raises $10M to Become World's Third-Largest LLM Platform

NEW YORK, Nov. 20, 2025 /PRNewswire/ -- Redrob, an AI research startup, today announced $10 million in Series A funding led by Korea Investment Partners, with participation from KB Investment, Kiwoom ...
Geeky Gadgets

Kimi K2 Thinking Leaps Ahead : Open Model Beats OpenAI & Google in Tests

What if the future of artificial intelligence wasn’t locked behind corporate walls but instead placed in the hands of everyone? Enter the Kimi K2 Thinking model, a new open source large language model ...
Forbes

How Mixed-Precision Quantization Could Break AI’s Power Addiction

It turns out the rapid growth of AI has a massive downside: namely, spiraling power consumption, strained infrastructure and runaway environmental damage. It’s clear the status quo won’t cut it ...
VentureBeat

Nvidia researchers unlock 4-bit LLM training that matches 8-bit performance

Researchers at Nvidia have developed a novel approach to train large language models (LLMs) in 4-bit quantized format while maintaining their stability and accuracy at the level of high-precision ...
Search Engine Land

LLM optimization in 2026: Tracking, visibility, and what’s next for AI discovery

Marketing, technology, and business leaders today are asking an important question: how do you optimize for large language models (LLMs) like ChatGPT, Gemini, and Claude? LLM optimization is taking ...
marktechpost

5 Common LLM Parameters Explained with Examples

Max Tokens is the maximum number of tokens the model can generate during a run. The model will try to stay within this limit across all turns. If it exceeds the specified number, the run will stop and ...
Hackaday

Making The Smallest And Dumbest LLM With Extreme Quantization

The reason why large language models are called ‘large’ is not because of how smart they are, but as a factor of their sheer size in bytes. At billions of parameters at four bytes each, they pose a ...
marktechpost

QeRL: NVFP4-Quantized Reinforcement Learning (RL) Brings 32B LLM Training to a Single H100—While Improving Exploration

What QeRL changes in the Reinforcement Learning (RL) loop? Most RLHF/GRPO/DAPO pipelines spend the bulk of wall-clock time in rollouts (token generation). QeRL shifts the policy’s weight path to NVFP4 ...