8 papers
CineMem: Attention-Aligned Fine-grained Memory Retrieval for Multi-Shot Long Video Generation
Xiaoxue Wu, Xinyu Gao, Fang Yu +2
Autoregressive video generation relies on memory retrieval to model long-range dependencies. This capability becomes particularly critical for multi-shot generation, where models m…
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models
Zichao Lin, Yifeng Xie, Bowen Qu +30
We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities of Multimodal Large Language Models (MLLMs). Existing benchmar…
ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions
Xiaoxue Wu, Xinyuan Chen, Yaohui Wang +1
Shot transitions play a pivotal role in multi-shot video generation, as they determine the overall narrative expression and the directorial design of visual storytelling. However,…
RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
Bingjie Gao, Qianli Ma, Xiaoxue Wu +9
Prompt design plays a crucial role in text-to-video (T2V) generation, yet user-provided prompts are often short, unstructured, and misaligned with training data, limiting the gener…
CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models
Xiaoxue Wu, Bingjie Gao, Yu Qiao +2
Despite significant advances in video synthesis, research into multi-shot video generation remains in its infancy. Even with scaled-up models and massive datasets, the shot transit…
The Devil is in the Prompts: Retrieval-Augmented Prompt Optimization for Text-to-Video Generation
Bingjie Gao, Xinyu Gao, Xiaoxue Wu +5
The evolution of Text-to-video (T2V) generative models, trained on large-scale datasets, has been marked by significant progress. However, the sensitivity of T2V generative models…
EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics
Xiaochuan Liu, Xin Cheng, Yuchong Sun +4
Imitating how humans move their gaze in a visual scene is a vital research problem for both visual understanding and psychology, kindling crucial applications such as building aliv…