Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Temporal State Transport in Video Generation: Diagnosing and Correcting Spectral Imbalance
Luyao Tang, Bingjun Luo, Dong Yi +5
Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual attributes such as identity…
cs.CV2025
HunyuanOCR Technical Report
Hunyuan Vision Team, Pengyuan Lyu, Xingyu Wan +29
This paper presents HunyuanOCR, a commercial-grade, open-source, and lightweight (1B parameters) Vision-Language Model (VLM) dedicated to OCR tasks. The architecture comprises a Na…
cs.CV2025
Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models
Hengzhuang Li, Xinsong Zhang, Qiming Peng +6
Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in multimodal tasks. Despite their impressive performance, MLLMs suffer from the modality imbalanc…