Picture for Jaeho Lee

Jaeho Lee

Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models

Add code
Mar 21, 2025
Viaarxiv icon

On the Internal Representations of Graph Metanetworks

Add code
Mar 12, 2025
Viaarxiv icon

Prompt-based Depth Pruning of Large Language Models

Add code
Feb 04, 2025
Viaarxiv icon

Fast Training of Sinusoidal Neural Fields via Scaling Initialization

Add code
Oct 07, 2024
Viaarxiv icon

Constructing a Singing Style Caption Dataset

Add code
Sep 15, 2024
Viaarxiv icon

AudioBERT: Audio Knowledge Augmented Language Model

Add code
Sep 12, 2024
Viaarxiv icon

Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher

Add code
Jun 26, 2024
Viaarxiv icon

Towards Federated Low-Rank Adaptation with Rank-Heterogeneous Communication

Add code
Jun 25, 2024
Viaarxiv icon

Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization

Add code
Jun 21, 2024
Viaarxiv icon

Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization

Add code
Jun 17, 2024
Viaarxiv icon