Picture for Zhi-Hong Deng

Zhi-Hong Deng

Keyword-Centric Prompting for One-Shot Event Detection with Self-Generated Rationale Enhancements

Add code
Aug 11, 2025
Viaarxiv icon

Mixture of Lookup Experts

Add code
Mar 20, 2025
Figure 1 for Mixture of Lookup Experts
Figure 2 for Mixture of Lookup Experts
Figure 3 for Mixture of Lookup Experts
Figure 4 for Mixture of Lookup Experts
Viaarxiv icon

SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs

Add code
Mar 20, 2025
Figure 1 for SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
Figure 2 for SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
Figure 3 for SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
Figure 4 for SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
Viaarxiv icon

BioMaze: Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning

Add code
Feb 23, 2025
Viaarxiv icon

Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model

Add code
Aug 19, 2024
Viaarxiv icon

Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning

Add code
Aug 13, 2024
Figure 1 for Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
Figure 2 for Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
Figure 3 for Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
Figure 4 for Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
Viaarxiv icon

Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning

Add code
May 09, 2024
Figure 1 for Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
Figure 2 for Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
Figure 3 for Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
Figure 4 for Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
Viaarxiv icon

Empowering Large Language Model Agents through Action Learning

Add code
Feb 24, 2024
Figure 1 for Empowering Large Language Model Agents through Action Learning
Figure 2 for Empowering Large Language Model Agents through Action Learning
Figure 3 for Empowering Large Language Model Agents through Action Learning
Figure 4 for Empowering Large Language Model Agents through Action Learning
Viaarxiv icon

Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy

Add code
Jul 31, 2023
Figure 1 for Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy
Figure 2 for Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy
Figure 3 for Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy
Figure 4 for Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy
Viaarxiv icon

Dual-Alignment Pre-training for Cross-lingual Sentence Embedding

Add code
May 16, 2023
Figure 1 for Dual-Alignment Pre-training for Cross-lingual Sentence Embedding
Figure 2 for Dual-Alignment Pre-training for Cross-lingual Sentence Embedding
Figure 3 for Dual-Alignment Pre-training for Cross-lingual Sentence Embedding
Figure 4 for Dual-Alignment Pre-training for Cross-lingual Sentence Embedding
Viaarxiv icon