Picture for Jianzong Wang

Jianzong Wang

Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference

Add code
Mar 30, 2025
Viaarxiv icon

VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection

Add code
Mar 28, 2025
Viaarxiv icon

RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations

Add code
Mar 28, 2025
Viaarxiv icon

Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy

Add code
Mar 13, 2025
Viaarxiv icon

ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression

Add code
Jan 13, 2025
Figure 1 for ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression
Figure 2 for ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression
Figure 3 for ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression
Figure 4 for ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression
Viaarxiv icon

CycleFlow: Leveraging Cycle Consistency in Flow Matching for Speaker Style Adaptation

Add code
Jan 03, 2025
Viaarxiv icon

Incremental Label Distribution Learning with Scalable Graph Convolutional Networks

Add code
Nov 20, 2024
Figure 1 for Incremental Label Distribution Learning with Scalable Graph Convolutional Networks
Figure 2 for Incremental Label Distribution Learning with Scalable Graph Convolutional Networks
Figure 3 for Incremental Label Distribution Learning with Scalable Graph Convolutional Networks
Figure 4 for Incremental Label Distribution Learning with Scalable Graph Convolutional Networks
Viaarxiv icon

ESARM: 3D Emotional Speech-to-Animation via Reward Model from Automatically-Ranked Demonstrations

Add code
Nov 20, 2024
Viaarxiv icon

IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding

Add code
Sep 29, 2024
Figure 1 for IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding
Figure 2 for IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding
Figure 3 for IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding
Figure 4 for IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding
Viaarxiv icon

PFID: Privacy First Inference Delegation Framework for LLMs

Add code
Jun 18, 2024
Figure 1 for PFID: Privacy First Inference Delegation Framework for LLMs
Figure 2 for PFID: Privacy First Inference Delegation Framework for LLMs
Figure 3 for PFID: Privacy First Inference Delegation Framework for LLMs
Figure 4 for PFID: Privacy First Inference Delegation Framework for LLMs
Viaarxiv icon