🔥 News

• [paper] 2025: Our paper on SubCLIP: Fine-Grained Visual-Semantic Alignment via Subtext Decomposition is accepted in ICVRV2025.
• [paper] 2025: Our paper on FlashMLA-ETAP: Efficient Transpose Attention Pipeline for Accelerating MLA Inference on NVIDIA H20 GPUs is accepted in ICONIP2025.
• [paper] 2025: Our paper on Radical Sequence Encoding with Fine-Tuned CLIP for Handwritten Chinese Character Recognition is accepted in ICDAR2025.
• [paper] 2025: Our paper on Challenges and Benchmarking of Object Detection Models on Edge AI SoCs is accepted in ICIC2025.
• [paper] 2025: Our paper on FPGA-Accelerated Error Diffusion Halftoning for High-Throughput Wide-Format Industrial Printing is accepted in CGI2025.