LLMs & Texto

CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive Tasks

Calibrated verifier telemetry enhances LLM agents in knowledge-intensive question answering by providing confidence scores and grounding verification, reducing both over-retrieval…

Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining

Training-time data augmentation techniques help mitigate overfitting in autoregressive language model pretraining by delaying performance deterioration and improving final model qu…

DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams

Agentic Data Tailoring paradigm uses learnable data processing to structure high-entropy multimodal streams, with DataClaw_0-9B model achieving robust alignment through SFT and GRP…

An Exploratory Case Study of LLM-Assisted Refactoring and Gameplay Feature Generation in an Endless Runner Game

Large language models demonstrate varying effectiveness in software development tasks, successfully completing localized refactoring but showing limitations in integrating new game…

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

EvoEmbedding is a dynamic embedding model that generates adaptive representations by maintaining a continuously updated latent memory, enabling improved retrieval performance in lo…

Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs

Tiered Language Models (TLMs) provide a framework for releasing large language models with configurable capability levels through secret keys that modify computation graphs while m…

Mia-AiLab/Gemmable-4-12B-MTP-GGUF

Modelo de modelo em alta no Hugging Face — 7.2 mil downloads e 40 curtidas da comunidade.

Mia-AiLab/Qwable-3.6-27b

Modelo de modelo em alta no Hugging Face — 24.0 mil downloads e 125 curtidas da comunidade.

AI inference startup Baseten reportedly raising $1.5B months after its last mega-round

Startup Baseten is reportedly close to finalizing a $1.5 billion round at a $13 billion as the “inference gold rush" marches on.

MosaicLeaks: Can your research agent keep a secret?

New usage analytics and updated spend controls for enterprises

OpenAI introduces new spend controls and usage analytics for ChatGPT Enterprise, helping organizations manage costs and scale AI with confidence.

unsloth/GLM-5.2-GGUF

Modelo de geração de texto em alta no Hugging Face — 41.8 mil downloads e 251 curtidas da comunidade.