5 papers
Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE
Haoyou Deng, Keyu Yan, Chaojie Mao +4
Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling diffusion models in visual generation. Recent advancements have focused on adaptively allocat…
The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders
Weiqin Yang, Yue Pan, Chongming Gao +4
We identify a critical pitfall in scaling transformer-based sequential recommenders: while increasing model size improves recommendation accuracy, it simultaneously amplifies popul…
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…
DMPT: Decoupled Modality-aware Prompt Tuning for Multi-modal Object Re-identification
Minghui Lin, Shu Wang, Xiang Wang +4
Current multi-modal object re-identification approaches based on large-scale pre-trained backbones (i.e., ViT) have displayed remarkable progress and achieved excellent performance…
Exploring the Evolution of Physics Cognition in Video Generation: A Survey
Minghui Lin, Xiang Wang, Yishan Wang +8
Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models. Despite this, their deficiencies in physical…