Picture for Pan Li

Pan Li

Dynamic Self-Distillation via Previous Mini-batches for Fine-tuning Small Language Models

Add code
Nov 25, 2024
Viaarxiv icon

Training Compute-Optimal Protein Language Models

Add code
Nov 04, 2024
Viaarxiv icon

LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation

Add code
Nov 04, 2024
Figure 1 for LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
Figure 2 for LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
Figure 3 for LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
Figure 4 for LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
Viaarxiv icon

Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

Add code
Oct 28, 2024
Viaarxiv icon

A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation

Add code
Oct 25, 2024
Viaarxiv icon

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors

Add code
Oct 13, 2024
Viaarxiv icon

Privately Learning from Graphs with Applications in Fine-tuning Large Language Models

Add code
Oct 10, 2024
Figure 1 for Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
Figure 2 for Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
Figure 3 for Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
Figure 4 for Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
Viaarxiv icon

A Benchmark on Directed Graph Representation Learning in Hardware Designs

Add code
Oct 09, 2024
Viaarxiv icon

Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness

Add code
Oct 01, 2024
Figure 1 for Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
Figure 2 for Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
Figure 3 for Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
Viaarxiv icon

Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answering

Add code
Aug 06, 2024
Figure 1 for Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answering
Figure 2 for Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answering
Figure 3 for Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answering
Figure 4 for Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answering
Viaarxiv icon