Picture for Yuhan Chen

Yuhan Chen

Callie

Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs

Add code
Feb 25, 2025
Viaarxiv icon

SymbioSim: Human-in-the-loop Simulation Platform for Bidirectional Continuing Learning in Human-Robot Interaction

Add code
Feb 11, 2025
Viaarxiv icon

HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation

Add code
Oct 28, 2024
Figure 1 for HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation
Figure 2 for HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation
Figure 3 for HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation
Figure 4 for HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation
Viaarxiv icon

Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification

Add code
Oct 22, 2024
Figure 1 for Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
Figure 2 for Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
Figure 3 for Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
Figure 4 for Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
Viaarxiv icon

Understanding the Performance and Estimating the Cost of LLM Fine-Tuning

Add code
Aug 08, 2024
Figure 1 for Understanding the Performance and Estimating the Cost of LLM Fine-Tuning
Figure 2 for Understanding the Performance and Estimating the Cost of LLM Fine-Tuning
Figure 3 for Understanding the Performance and Estimating the Cost of LLM Fine-Tuning
Figure 4 for Understanding the Performance and Estimating the Cost of LLM Fine-Tuning
Viaarxiv icon

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

Add code
Aug 03, 2024
Figure 1 for STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
Figure 2 for STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
Figure 3 for STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
Figure 4 for STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
Viaarxiv icon

YuLan: An Open-source Large Language Model

Add code
Jun 28, 2024
Figure 1 for YuLan: An Open-source Large Language Model
Figure 2 for YuLan: An Open-source Large Language Model
Figure 3 for YuLan: An Open-source Large Language Model
Figure 4 for YuLan: An Open-source Large Language Model
Viaarxiv icon

Mixture of In-Context Experts Enhance LLMs' Long Context Awareness

Add code
Jun 28, 2024
Figure 1 for Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
Figure 2 for Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
Figure 3 for Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
Figure 4 for Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
Viaarxiv icon

MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability

Add code
May 23, 2024
Figure 1 for MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
Figure 2 for MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
Figure 3 for MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
Figure 4 for MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
Viaarxiv icon

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models

Add code
Apr 09, 2024
Viaarxiv icon