University of Michigan

university

Verified

https://umich.edu/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

xunzhou authored a paper 16 days ago

Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models

xunzhou authored a paper about 1 month ago

Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling

emozilla authored a paper 3 months ago

DeMo: Decoupled Momentum Optimization

View all activity

umich's activity

xunzhou

authored a paper 16 days ago

Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models

Paper • 2502.15499 • Published 21 days ago • 13

Mishamq

authored a paper 23 days ago

HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model

Paper • 2502.10807 • Published 27 days ago • 3

Mishamq

authored a paper 24 days ago

NatureLM: Deciphering the Language of Nature for Scientific Discovery

Paper • 2502.07527 • Published about 1 month ago • 19

eienmojiki

posted an update about 1 month ago

Post

2116

🪄 LayerDiffuse - Flux Version (Demo) 🪄

LayerDiffuse - Transparent Image Layer Diffusion using Latent Transparency

Demo: https://huggingface.co/spaces/eienmojiki/Flux-LayerDiffuse

3 replies

·

xunzhou

authored a paper about 1 month ago

Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling

Paper • 2501.16975 • Published Jan 28 • 26

cwoolee

authored a paper 4 months ago

BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference

Paper • 2410.21262 • Published Oct 28, 2024 • 1

Ekdeep

authored 5 papers 5 months ago

In-Context Learning Dynamics with Random Binary Sequences

Paper • 2310.17639 • Published Oct 26, 2023

Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space

Paper • 2406.19370 • Published Jun 27, 2024 • 1

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

Paper • 2311.12786 • Published Nov 21, 2023 • 2

Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model

Paper • 2402.07757 • Published Feb 12, 2024

Mechanistic Mode Connectivity

Paper • 2211.08422 • Published Nov 15, 2022

xunzhou

authored a paper 5 months ago

Hyper-Connections

Paper • 2409.19606 • Published Sep 29, 2024 • 23

Yinpei

authored 6 papers 6 months ago

A Survey on Dialog Management: Recent Advances and Challenges

Paper • 2005.02233 • Published May 5, 2020

SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents

Paper • 2305.13040 • Published May 22, 2023 • 2

GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection

Paper • 2111.14592 • Published Nov 29, 2021 • 1

Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation

Paper • 2310.07968 • Published Oct 12, 2023

Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking

Paper • 2106.00291 • Published Jun 1, 2021

RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning

Paper • 2409.14674 • Published Sep 23, 2024 • 43

cwoolee

authored a paper 7 months ago

Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks

Paper • 2310.18882 • Published Oct 29, 2023 • 1

kumo24

updated a model 8 months ago

umich/gpt2-sentiment-nuclear

Text Classification • Updated Jul 29, 2024 • 109