Maosong Sun

A look into how MLLMs handle small details in images.

ProSparse improves activation sparsity in LLMs for better efficiency and performance.

Examining grokking, double descent, and emergent abilities in deep learning models.

bGPT focuses on binary data for better digital modeling and predictions.

A look at the importance of aligning AI systems with human values.

New model improves image processing in multimodal systems.

EREN enhances the accuracy of language models through effective editing techniques.

New models enhance reasoning skills across various tasks, improving AI performance.

GUICourse aims to improve interaction with digital interfaces through targeted datasets for GUI agents.

MelodyT5 offers a new approach to music creation and analysis using symbolic notation.

Examining how LLMs can add numbers without explicit steps.

Research aims to develop language models with unique personalities for better human-like interactions.

A new framework enhances evaluation of RAG systems in specialized domains.

MiniCPM-V enhances AI use on mobile devices with efficiency and performance.

FastFiD improves ODQA efficiency by selecting key sentences for quicker answers.

A new approach to tokenization enhances analysis of ancient scripts.

Exploring the efficiency and adaptability of language models through modular design.

Exploring activation sparsity to improve language model efficiency.

KBAlign helps machines learn faster and more effectively through self-questioning techniques.

A groundbreaking approach to studying word meanings across languages.

Explore how large language models are becoming more efficient and accessible.

A new method combines autoregressive and diffusion models for better media generation.