412 citations · 698 across the 17 of their papers we have counts for
17 papers
Expressivity Saturation: Reduced Affine Region Usage Under Increasing Task Complexity
Xuan Qi, Yi Wei, Fanqi Yu +1
Piecewise-affine neural networks (e.g., with ReLU or LeakyReLU activations) implement continuous piecewise-affine maps, and the number of affine regions provides a natural proxy fo…
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…
ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws
Ruihang Li, Yixuan Wei, Miaosen Zhang +3
High-quality data is crucial for the pre-training performance of large language models. Unfortunately, existing quality filtering methods rely on a known high-quality dataset as re…
Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
Miaosen Zhang, Yixuan Wei, Zhen Xing +8
Modern vision models are trained on very large noisy datasets. While these models acquire strong capabilities, they may not follow the user's intent to output the desired results i…
Xwin-LM: Strong and Scalable Alignment Practice for LLMs
Bolin Ni, JingCheng Hu, Yixuan Wei +4
In this work, we present Xwin-LM, a comprehensive suite of alignment methodologies for large language models (LLMs). This suite encompasses several key techniques, including superv…
Common 7B Language Models Already Possess Strong Math Capabilities
Chen Li, Weiqi Wang, Jingcheng Hu +5
Mathematical capabilities were previously believed to emerge in common language models only at a very large scale or require extensive math-related pre-training. This paper shows t…
FP8-LM: Training FP8 Large Language Models
Houwen Peng, Kan Wu, Yixuan Wei +17
In this paper, we explore FP8 low-bit data formats for efficient training of large language models (LLMs). Our key insight is that most variables, such as gradients and optimizer s…
Human Pose as Compositional Tokens
Zigang Geng, Chunyu Wang, Yixuan Wei +3
Human pose is typically represented by a coordinate vector of body joints or their heatmap embeddings. While easy for data processing, unrealistic pose estimates are admitted due t…
Exploring Discrete Diffusion Models for Image Captioning
Zixin Zhu, Yixuan Wei, Jianfeng Wang +7
The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name…
Attentive Mask CLIP
Yifan Yang, Weiquan Huang, Yixuan Wei +8
Image token removal is an efficient augmentation strategy for reducing the cost of computing image features. However, this efficient augmentation strategy has been found to adverse…
On Data Scaling in Masked Image Modeling
Zhenda Xie, Zheng Zhang, Yue Cao +4
An important goal of self-supervised learning is to enable model pre-training to benefit from almost unlimited data. However, one method that has recently become popular, namely ma…
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation
Yixuan Wei, Han Hu, Zhenda Xie +5
Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classificat…
iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition
Yixuan Wei, Yue Cao, Zheng Zhang +4
Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning thro…
Swin Transformer V2: Scaling Up Capacity and Resolution
Ze Liu, Han Hu, Yutong Lin +9
Large-scale NLP models have been shown to significantly improve the performance on language tasks with no signs of saturation. They also demonstrate amazing few-shot capabilities l…
Video Swin Transformer
Ze Liu, Jia Ning, Yue Cao +4
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchm…
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Ze Liu, Yutong Lin, Yue Cao +5
This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer fro…
DeepHuman: 3D Human Reconstruction from a Single Image
Zerong Zheng, Tao Yu, Yixuan Wei +2
We propose DeepHuman, an image-guided volume-to-volume translation CNN for 3D human reconstruction from a single RGB image. To reduce the ambiguities associated with the surface ge…