Kaifeng Lyu

vfleaking's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 7 months ago

LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?

Paper • 2503.19990 • Published Mar 25 • 35

authored 7 papers over 1 year ago

Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing

Paper • 2301.11500 • Published Jan 27, 2023

DistillSpec: Improving Speculative Decoding via Knowledge Distillation

Paper • 2310.08461 • Published Oct 12, 2023 • 1

On the SDEs and Scaling Rules for Adaptive Gradient Algorithms

Paper • 2205.10287 • Published May 20, 2022

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Paper • 2311.18817 • Published Nov 30, 2023

RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval

Paper • 2402.18510 • Published Feb 28, 2024

A Quadratic Synchronization Rule for Distributed Deep Learning

Paper • 2310.14423 • Published Oct 22, 2023

The Marginal Value of Momentum for Small Learning Rate SGD

Paper • 2307.15196 • Published Jul 27, 2023