LLMs & Texto

Paper LLMs & Texto

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

MemSlides presents a hierarchical memory framework for personalized presentation agents that separates long-term user profiles, working memory for session constraints, and tool mem…

15.06.2026 ·▲ 14

Blog LLMs & Texto

Introducing the OpenAI Partner Network

OpenAI launches the Partner Network, investing $150M to help global partners accelerate enterprise AI adoption, deployment, and transformation.

14.06.2026

Paper LLMs & Texto

Selective Synergistic Learning for Video Object-Centric Learning

Selective Synergistic Learning (SSync) addresses limitations in video object-centric learning by selectively distilling reliable cues through pseudo-labeling and transitive merging…

14.06.2026 ·▲ 3

Paper LLMs & Texto

Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations

A novel approach for B2B conversation classification that reduces token usage by 99% while improving performance and maintaining robustness as context length increases.

14.06.2026 ·▲ 2

Paper Robótica & RL

AC-ODM: Actor--Critic Online Data Mixing for Sample-Efficient LLM Pretraining

AC-ODM optimizes pretraining data composition for LLMs using reinforcement learning to improve convergence speed and downstream accuracy while maintaining computational efficiency.

14.06.2026 ·▲ 1

Modelo Geração de Imagem

SulphurAI/Sulphur-2-base

Modelo de geração de vídeo em alta no Hugging Face — 932.8 mil downloads e 1.7 mil curtidas da comunidade.

13.06.2026 ·↓ 932787

Blog LLMs & Texto

Anthropic shuts down Fable, Mythos models following Trump admin directive

Commerce dept. worries that a Fable 5 "jailbreak" could be a national security threat.

13.06.2026

Paper LLMs & Texto

ReSyn: A Generalized Recursive Regular Expression Synthesis Framework

A divide-and-conquer framework named ReSyn enhances regex synthesis accuracy by decomposing complex problems, combined with a parameter-efficient synthesizer called Set2Regex that…

13.06.2026 ·▲ 2

Modelo LLMs & Texto

nvidia/Qwen3.6-35B-A3B-NVFP4

Modelo de geração de texto em alta no Hugging Face — 4.5 mi downloads e 309 curtidas da comunidade.

12.06.2026 ·↓ 4483855

Blog LLMs & Texto

NVIDIA Blackwell Leads on First Agentic AI Infrastructure Benchmark

AgentPerf from Artificial Analysis, the industry’s first agentic AI benchmark, gives developers, enterprises and infrastructure providers a clear way to compare systems for agentic AI. In the first round of published results, the NVIDIA Blackwell Ultra NVL72 platform delivers leading performance across the agentic AI workloads tested, running 20x more agents per megawatt than NVIDIA […]

12.06.2026

Blog LLMs & Texto

Ire identifies another LOTUSLITE specimen

Project Ire examined a timely malware sample and determined its intent through reverse engineering—identifying LOTUSLITE characteristics even as most major EDR tools did not detect it. The post Ire identifies another LOTUSLITE specimen appeared first on Microsoft Research .

12.06.2026

Blog LLMs & Texto

Here's what Jeff Bezos' new startup Prometheus will do

It isn't the only startup tackling physical AI, but it's one of the best-funded.

12.06.2026