Picture for Jianjian Cao

Jianjian Cao

Local Information Matters: Inference Acceleration For Grounded Conversation Generation Models Through Adaptive Local-Aware Token Pruning

Add code
Apr 01, 2025
Viaarxiv icon

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models

Add code
Mar 13, 2025
Viaarxiv icon

DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models

Add code
Mar 03, 2025
Viaarxiv icon

$Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers

Add code
Jun 03, 2024
Figure 1 for $Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
Figure 2 for $Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
Figure 3 for $Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
Figure 4 for $Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
Viaarxiv icon

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

Add code
Mar 05, 2024
Viaarxiv icon

ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation

Add code
Jan 29, 2024
Figure 1 for ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation
Figure 2 for ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation
Figure 3 for ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation
Figure 4 for ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation
Viaarxiv icon

Collaborative Position Reasoning Network for Referring Image Segmentation

Add code
Jan 22, 2024
Viaarxiv icon

LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark

Add code
Jun 18, 2023
Figure 1 for LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark
Figure 2 for LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark
Figure 3 for LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark
Figure 4 for LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark
Viaarxiv icon

A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification

Add code
Feb 23, 2023
Figure 1 for A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification
Figure 2 for A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification
Figure 3 for A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification
Figure 4 for A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification
Viaarxiv icon

JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment

Add code
Feb 20, 2023
Figure 1 for JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment
Figure 2 for JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment
Figure 3 for JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment
Figure 4 for JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment
Viaarxiv icon