8 citations · 12 across the 12 of their papers we have counts for
14 papers
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Zhiheng Liu, Weiming Ren, Xiaoke Huang +12
Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the t…
A Systematic Post-Train Framework for Video Generation
Zeyue Xue, Siming Fu, Jie Huang +9
While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a significant gap remains between th…
INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats
Mengzhao Chen, Meng Wu, Hui Jin +10
Modern AI hardware, such as Nvidia's Blackwell architecture, is increasingly embracing low-precision floating-point (FP) formats to handle the pervasive activation outliers in Larg…
Parallel Loop Transformer for Efficient Test-Time Computation Scaling
Bohong Wu, Mengzhao Chen, Xiang Luo +9
Large Language Models (LLMs) are powerful but often too slow and costly for real-world use during inference. Looped transformers save on parameters by reusing the same weights for…
WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception
Zhiheng Liu, Xueqing Deng, Shoufa Chen +7
Generative video modeling has made significant strides, yet ensuring structural and temporal consistency over long sequences remains a challenge. Current methods predominantly rely…
Model Merging in Pre-training of Large Language Models
Yunshui Li, Yiyuan Ma, Shen Yan +23
Model merging has emerged as a promising technique for enhancing large language models, though its application in large-scale pre-training remains relatively unexplored. In this pa…
Scaling Law for Quantization-Aware Training
Mengzhao Chen, Chaoyi Zhang, Jing Liu +8
Large language models (LLMs) demand substantial computational and memory resources, creating deployment challenges. Quantization-aware training (QAT) addresses these challenges by…
DanceGRPO: Unleashing GRPO on Visual Generation
Zeyue Xue, Jie Wu, Yu Gao +8
Recent advances in generative AI have revolutionized visual content creation, yet aligning model outputs with human preferences remains a critical challenge. While Reinforcement Le…
Enhance-A-Video: Better Generated Video for Free
Yang Luo, Xuanlei Zhao, Mengzhao Chen +5
DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free ap…
LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
Jiahao Wang, Ning Kang, Lewei Yao +12
In this paper, we investigate how to convert a pre-trained Diffusion Transformer (DiT) into a linear DiT, as its simplicity, parallelism, and efficiency for image generation. Throu…
PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization
Mengzhao Chen, Yi Liu, Jiahao Wang +3
Existing weight-activation quantization methods for Large Language Models (LLMs) primarily address channel-wise outliers but often neglect token-wise outliers, which limits the acc…
EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
Mengzhao Chen, Wenqi Shao, Peng Xu +4
Large language models (LLMs) are crucial in modern natural language processing and artificial intelligence. However, they face challenges in managing their significant memory requi…
Adapting LLaMA Decoder to Vision Transformer
Jiahao Wang, Wenqi Shao, Mengzhao Chen +7
This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We…
BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
Peng Xu, Wenqi Shao, Mengzhao Chen +6
Large language models (LLMs) have demonstrated outstanding performance in various tasks, such as text summarization, text question-answering, and etc. While their performance is im…