Picture for Hao Tang

Hao Tang

GWQ: Gradient-Aware Weight Quantization for Large Language Models

Add code
Oct 30, 2024
Figure 1 for GWQ: Gradient-Aware Weight Quantization for Large Language Models
Figure 2 for GWQ: Gradient-Aware Weight Quantization for Large Language Models
Figure 3 for GWQ: Gradient-Aware Weight Quantization for Large Language Models
Figure 4 for GWQ: Gradient-Aware Weight Quantization for Large Language Models
Viaarxiv icon

MobA: A Two-Level Agent System for Efficient Mobile Task Automation

Add code
Oct 17, 2024
Figure 1 for MobA: A Two-Level Agent System for Efficient Mobile Task Automation
Figure 2 for MobA: A Two-Level Agent System for Efficient Mobile Task Automation
Figure 3 for MobA: A Two-Level Agent System for Efficient Mobile Task Automation
Figure 4 for MobA: A Two-Level Agent System for Efficient Mobile Task Automation
Viaarxiv icon

Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention

Add code
Oct 14, 2024
Viaarxiv icon

VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers

Add code
Oct 10, 2024
Figure 1 for VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers
Figure 2 for VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers
Figure 3 for VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers
Figure 4 for VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers
Viaarxiv icon

OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB

Add code
Oct 09, 2024
Figure 1 for OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB
Figure 2 for OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB
Figure 3 for OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB
Figure 4 for OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB
Viaarxiv icon

Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robots

Add code
Oct 02, 2024
Figure 1 for Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robots
Figure 2 for Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robots
Figure 3 for Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robots
Figure 4 for Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robots
Viaarxiv icon

Brain Tumor Classification on MRI in Light of Molecular Markers

Add code
Sep 29, 2024
Figure 1 for Brain Tumor Classification on MRI in Light of Molecular Markers
Figure 2 for Brain Tumor Classification on MRI in Light of Molecular Markers
Figure 3 for Brain Tumor Classification on MRI in Light of Molecular Markers
Figure 4 for Brain Tumor Classification on MRI in Light of Molecular Markers
Viaarxiv icon

A Simple HMM with Self-Supervised Representations for Phone Segmentation

Add code
Sep 15, 2024
Figure 1 for A Simple HMM with Self-Supervised Representations for Phone Segmentation
Figure 2 for A Simple HMM with Self-Supervised Representations for Phone Segmentation
Figure 3 for A Simple HMM with Self-Supervised Representations for Phone Segmentation
Figure 4 for A Simple HMM with Self-Supervised Representations for Phone Segmentation
Viaarxiv icon

Estimating the Completeness of Discrete Speech Units

Add code
Sep 09, 2024
Figure 1 for Estimating the Completeness of Discrete Speech Units
Figure 2 for Estimating the Completeness of Discrete Speech Units
Figure 3 for Estimating the Completeness of Discrete Speech Units
Figure 4 for Estimating the Completeness of Discrete Speech Units
Viaarxiv icon

Property Neurons in Self-Supervised Speech Transformers

Add code
Sep 07, 2024
Figure 1 for Property Neurons in Self-Supervised Speech Transformers
Figure 2 for Property Neurons in Self-Supervised Speech Transformers
Figure 3 for Property Neurons in Self-Supervised Speech Transformers
Figure 4 for Property Neurons in Self-Supervised Speech Transformers
Viaarxiv icon