machine learning research topics 2023

Subscribe to the PwC Newsletter

Join the community, trending research, dreamclear: high-capacity real-world image restoration with privacy-safe dataset curation.

Our second contribution, DreamClear, is a DiT-based image restoration model.

Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation

To facilitate the scale-up of Emilia, we also present Emilia-Pipe, the first open-source preprocessing pipeline designed to efficiently transform raw, in-the-wild speech data into high-quality training data with speech annotations.

MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer

The recent large-scale text-to-speech (TTS) systems are usually grouped as autoregressive and non-autoregressive systems.

Docling Technical Report

This technical report introduces Docling, an easy to use, self-contained, MIT-licensed open-source package for PDF document conversion.

OmniGen: Unified Image Generation

In this work, we introduce OmniGen, a new diffusion model for unified image generation.

KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation

openspg/kag • 10 Sep 2024

The recently developed retrieval-augmented generation (RAG) technology has enabled the efficient construction of domain-specific applications.

Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving

hustvl/senna • 29 Oct 2024

In contrast, Large Vision-Language Models (LVLMs) excel in scene understanding and reasoning.

D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement

When pretrained on Objects365, D-FINE-L / X attains 57. 1% / 59. 3% AP, surpassing all existing real-time detectors.

Data Formulator 2: Iteratively Creating Rich Visualizations with AI

microsoft/data-formulator • 28 Aug 2024

To create rich visualizations, data analysts often need to iterate back and forth among data processing and chart specification to achieve their goals.

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

By treating model parameters as tokens, we replace all the linear projections in Transformers with our token-parameter attention layer, where input tokens act as queries and model parameters as keys and values.