Picture for Jingwei Sun

Jingwei Sun

Helen

SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval

Add code
Dec 16, 2024
Viaarxiv icon

LoBAM: LoRA-Based Backdoor Attack on Model Merging

Add code
Nov 23, 2024
Viaarxiv icon

A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models

Add code
Oct 08, 2024
Viaarxiv icon

Latent Feature and Attention Dual Erasure Attack against Multi-View Diffusion Models for 3D Assets Protection

Add code
Aug 21, 2024
Figure 1 for Latent Feature and Attention Dual Erasure Attack against Multi-View Diffusion Models for 3D Assets Protection
Figure 2 for Latent Feature and Attention Dual Erasure Attack against Multi-View Diffusion Models for 3D Assets Protection
Figure 3 for Latent Feature and Attention Dual Erasure Attack against Multi-View Diffusion Models for 3D Assets Protection
Figure 4 for Latent Feature and Attention Dual Erasure Attack against Multi-View Diffusion Models for 3D Assets Protection
Viaarxiv icon

Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedback

Add code
May 30, 2024
Viaarxiv icon

Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models

Add code
Apr 03, 2024
Figure 1 for Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models
Figure 2 for Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models
Figure 3 for Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models
Figure 4 for Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models
Viaarxiv icon

Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents

Add code
Dec 03, 2023
Figure 1 for Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents
Figure 2 for Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents
Figure 3 for Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents
Figure 4 for Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents
Viaarxiv icon

SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models

Add code
Oct 29, 2023
Figure 1 for SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
Figure 2 for SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
Figure 3 for SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
Figure 4 for SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
Viaarxiv icon

FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models

Add code
Oct 02, 2023
Figure 1 for FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
Figure 2 for FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
Figure 3 for FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
Figure 4 for FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
Viaarxiv icon

FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data

Add code
Sep 18, 2023
Viaarxiv icon