Multimedia Processing and Coding
Applications of LLMs in video coding, compression, and multimedia processing for efficient data representation
Multimedia Processing and Coding
Research on Large Language Models in Multimedia Processing and Coding
Revolutionizing Video Compression with AI
Harnessing Multimodal LLMs for Efficient Video Coding
Auditory LLMs for Speech Quality Evaluation
Advancing automated speech assessment through large language models
Accelerating Video LLMs with Dynamic Token Compression
Solving the efficiency bottleneck in video processing models
Error-Resilient Image Compression
Making neural image codecs robust against packet loss
Bridging Modalities in AI
Understanding Connectors in Multi-modal LLMs
Rethinking Position Embeddings for Video LLMs
Enhancing video understanding with VRoPE architecture
Real-Time Video Intelligence: ReKV
Enabling streaming video question-answering without reprocessing
STORM: Revolutionizing Long Video Analysis
Token-Efficient Processing for Multimodal LLMs
Next-Gen Video Understanding
Boosting Inference Efficiency with Image Packing & AoE Architecture
Making Video LLMs Faster & Lighter
1.x-Bit KV Cache Quantization for Memory Efficiency
Dynamic Token Representation for Video LLMs
Overcoming efficiency barriers in video processing for large language models
Efficient Text-to-Video Generation
Making Video AI Accessible for Resource-Limited Devices
Next-Gen Video Compression
GIViC: Reimagining Video Compression with Generative AI
