OpenAI describes GPT-Live, its third-generation voice system, which removes the traditional turn-detector component and instead streams audio continuously through a…
Hugging Face contributor sergiopaniego published a guide describing a framework for training coding agents using TRL’s AsyncGRPO algorithm together with…
Simon Willison released version 0.32 of his LLM command-line tool and Python library on August 4, 2026, adding support for…
Researchers introduce RestoreKV, a technique that addresses the accuracy loss large language models suffer under aggressive key-value cache eviction by…
Researchers Şuayp Talha Kocabay, Talha Rüzgar Akkuş, and Kamer Ali Yüksel of aiXplain propose ARCHead, a method for compressing the…
A team including Sitong Gong, Caixin Kang, and Yifei Huang presents GROVE, a training-free framework that organizes streaming video into…
Researchers propose TurnSight, a framework for multi-turn tool-integrated reasoning that addresses the credit-assignment problem by deriving training supervision from an…
Researchers including Wanshun Su, Yang Shi, and Feihu Liu, working across Northwestern Polytechnical University, Peking University, Alibaba Group, and Tsinghua…
A community project trained NanoColibri-Instruct, a 2.7-billion-parameter mixture-of-experts model, for a total cost of roughly $180-260 using a “relay pretraining”…
Bekko Embedding is a family of compact multilingual retrieval models built through layer pruning and contrastive learning. Its smaller variant,…
Liquid AI released two encoder models, LFM2.5-Encoder-230M and -350M, built for efficient long-context processing on CPU by converting decoder architectures…
OpenAI described engineering work, partly performed autonomously by its GPT-5.6 “Sol” model, to optimize the production software that serves its…
