3 papers
cs.CV2026
GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression
Ziyue Zeng, Dingjie Peng, Xun Su +1
Codebook-driven generative compression uses a pretrained image or video generator as a zero-shot visual prior and transmits compact codebook indices to guide reconstruction at ultr…
cs.CV2024
Time Step Generating: A Universal Synthesized Deepfake Image Detector
Ziyue Zeng, Haoyuan Liu, Dingjie Peng +2
Currently, high-fidelity text-to-image models are developed in an accelerating pace. Among them, Diffusion Models have led to a remarkable improvement in the quality of image gener…
cs.CL2024
Evaluating Large Language Models on Financial Report Summarization: An Empirical Study
Xinqi Yang, Scott Zang, Yong Ren +2
In recent years, Large Language Models (LLMs) have demonstrated remarkable versatility across various applications, including natural language understanding, domain-specific knowle…