4 papers
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +315
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…
AttenTrack: Mobile User Attention Awareness Based on Context and External Distractions
Yutong Lin, Suyuan Liu, Kaiwen Guo +3
In the mobile internet era, managing limited attention amid information overload is crucial for enhancing collaboration and information delivery. However, current attention-aware s…
MAGI-1: Autoregressive Video Generation at Scale
Sand. ai, Hansi Teng, Hongyu Jia +36
We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to…
Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation
Shaoyuan Chen, Wencong Xiao, Yutong Lin +5
Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient…