Picture for Shiqi Jiang

Shiqi Jiang

Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment

Add code
Mar 21, 2025
Viaarxiv icon

StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition

Add code
Mar 08, 2025
Viaarxiv icon

Interleaved Block-based Learned Image Compression with Feature Enhancement and Quantization Error Compensation

Add code
Feb 21, 2025
Viaarxiv icon

FD-LSCIC: Frequency Decomposition-based Learned Screen Content Image Compression

Add code
Feb 21, 2025
Viaarxiv icon

The Potential and Value of AI Chatbot in Personalized Cognitive Training

Add code
Oct 25, 2024
Figure 1 for The Potential and Value of AI Chatbot in Personalized Cognitive Training
Figure 2 for The Potential and Value of AI Chatbot in Personalized Cognitive Training
Figure 3 for The Potential and Value of AI Chatbot in Personalized Cognitive Training
Viaarxiv icon

Making Every Frame Matter: Continuous Video Understanding for Large Models via Adaptive State Modeling

Add code
Oct 19, 2024
Viaarxiv icon

SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds

Add code
Sep 16, 2024
Viaarxiv icon

Advancing Multi-Modal Sensing Through Expandable Modality Alignment

Add code
Jul 25, 2024
Viaarxiv icon

Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution

Add code
Jul 11, 2024
Viaarxiv icon

OMR-NET: a two-stage octave multi-scale residual network for screen content image compression

Add code
Jul 11, 2024
Figure 1 for OMR-NET: a two-stage octave multi-scale residual network for screen content image compression
Figure 2 for OMR-NET: a two-stage octave multi-scale residual network for screen content image compression
Figure 3 for OMR-NET: a two-stage octave multi-scale residual network for screen content image compression
Figure 4 for OMR-NET: a two-stage octave multi-scale residual network for screen content image compression
Viaarxiv icon