4 papers
TextSculptor: Training and Benchmarking Scene Text Editing
Yiheng Lin, Siyu Jiao, Xiaohan Lan +12
Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editi…
Attn-QAT: 4-Bit Attention With Quantization-Aware Training
Peiyuan Zhang, Matthew Noto, Wenxuan Tan +4
Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the main obstacle due to FP4's tiny dynamic…
Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
Haoran You, Connelly Barnes, Yuqian Zhou +10
Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) image generation quality but suffer from high latency and memory inefficiency, making them difficult to deploy o…
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
Haoran You, Yipin Guo, Yichao Fu +6
Large language models (LLMs) have shown impressive performance on language tasks but face challenges when deployed on resource-constrained devices due to their extensive parameters…