Personalizing black-box models for nonparametric regression with minimax optimality

⋅

arXiv:2601.01432v1 Announce Type: cross Abstract: Recent advances in large-scale models, including deep neural networks and large language models, have substantially improved performance across a wide range of learning tasks. The widespread availability of such pre-trained models creates new opportunities for data-efficient statistical learning, provided they can be effectively integrated into downstream tasks. Motivated by this setting, we study few-shot personalization, where a pre-trained black-box model is adapted to a target domain using a limited number of samples. We […]

Ver mais

Liked Liked

Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey

⋅

arXiv:2601.03262v1 Announce Type: new Abstract: Visually rich documents (VRDs) challenge retrieval-augmented generation (RAG) with layout-dependent semantics, brittle OCR, and evidence spread across complex figures and structured tables. This survey examines how Multimodal Large Language Models (MLLMs) are being used to make VRD retrieval practical for RAG. We organize the literature into three roles: Modality-Unifying Captioners, Multimodal Embedders, and End-to-End Representers. We compare these roles along retrieval granularity, information fidelity, latency and index size, and compatibility with reranking and […]

Ver mais

Liked Liked

Introducing GPT-5.2-Codex

⋅

GPT-5.2-Codex is OpenAI’s most advanced coding model, offering long-horizon reasoning, large-scale code transformations, and enhanced cybersecurity capabilities.

Ver mais

Liked Liked
LLM Server GPU Picks for 2026: H100, A100, B200, RTX A6000

LLM Server GPU Picks for 2026: H100, A100, B200, RTX A6000

⋅

A team spins up LLM serving on the GPU they can grab the fastest. The first days look great, but after real traffic shows up, your memory fills up way faster than you’d expect, your latency gets all uneven, and keeping the system stable becomes your main job. From our side of the stack, GPU choice isn’t usually about the highest benchmark scores. What really matters is whether the model weights and KV cache fit without constant tuning, how […]

Ver mais

Liked Liked

Ford Outlines AI Assistant and BlueCruise Roadmap at CES 2026

⋅

Key Highlights: Ford Pushes Deeper Into AI and Hands-Free Driving at CES 2026 Ford Motor Company unveiled plans for an AI-powered digital assistant and a next-generation version of its BlueCruise driver-assistance system at the Consumer Electronics Show 2026 in Las Vegas, outlining its latest push toward software-driven and hands-free vehicle technologies. The announcements were made during a “Great Minds” speaker session at CES, rather than a headline keynote, reflecting a more measured presence from the automaker at the […]

Ver mais

Liked Liked

Robotic Assembly Using Deep Reinforcement Learning

⋅

Introduction Disclaimer: This article is a cross post from Pytorch Medium Blog Post. One of the most exciting advancements, that has pushed the frontier of the Artificial Intelligence (AI) in recent years, is Deep Reinforcement Learning (DRL). DRL belongs to the family of machine learning algorithms. It assumes that intelligent machines can learn from their actions similar to the way humans learn from experience. Over the recent years we could witness some impressive real-world applications of DRL. The […]

Ver mais

Liked Liked
Running Mistral 8x7Bs Mixture of Experts on a Macbook

Running Mistral 8x7Bs Mixture of Experts on a Macbook

⋅

Below are the steps I used to get Mistral 8x7Bs Mixture of Experts (MOE) model running locally on my Macbook (with its Apple M2 chip and 24 GB of memory). Here’s a great overview of the model for anyone interested in learning more. Short version: The Mistral “Mixtral” 8x7B 32k model,developed by Mistral AI, is a Mixture of Experts (MoE) model designed to enhance machine understanding and generation of text. Similar to GPT-4, Mixtral-8x7b uses a Mixture of […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2025