Picture for Yiming Chen

Yiming Chen

Human-Like Robot Impedance Regulation Skill Learning from Human-Human Demonstrations

Add code
Feb 19, 2025
Viaarxiv icon

A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models

Add code
Feb 11, 2025
Viaarxiv icon

PAL: Prompting Analytic Learning with Missing Modality for Multi-Modal Class-Incremental Learning

Add code
Jan 16, 2025
Viaarxiv icon

Transferable Adversarial Attacks against ASR

Add code
Nov 14, 2024
Figure 1 for Transferable Adversarial Attacks against ASR
Figure 2 for Transferable Adversarial Attacks against ASR
Figure 3 for Transferable Adversarial Attacks against ASR
Viaarxiv icon

VoiceBench: Benchmarking LLM-Based Voice Assistants

Add code
Oct 22, 2024
Viaarxiv icon

Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures

Add code
Oct 10, 2024
Viaarxiv icon

DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation

Add code
Oct 09, 2024
Figure 1 for DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
Figure 2 for DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
Figure 3 for DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
Figure 4 for DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
Viaarxiv icon

Topology-Agnostic Graph U-Nets for Scalar Field Prediction on Unstructured Meshes

Add code
Oct 08, 2024
Figure 1 for Topology-Agnostic Graph U-Nets for Scalar Field Prediction on Unstructured Meshes
Figure 2 for Topology-Agnostic Graph U-Nets for Scalar Field Prediction on Unstructured Meshes
Figure 3 for Topology-Agnostic Graph U-Nets for Scalar Field Prediction on Unstructured Meshes
Figure 4 for Topology-Agnostic Graph U-Nets for Scalar Field Prediction on Unstructured Meshes
Viaarxiv icon

Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models

Add code
Sep 27, 2024
Figure 1 for Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models
Figure 2 for Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models
Figure 3 for Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models
Figure 4 for Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models
Viaarxiv icon

Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization

Add code
Sep 16, 2024
Figure 1 for Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization
Figure 2 for Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization
Figure 3 for Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization
Figure 4 for Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization
Viaarxiv icon