5 citations · 11 across the 11 of their papers we have counts for
12 papers
The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path
Yiheng Tao, Kaiwen Cheng, Yao Lu +2
Large Language Models (LLMs) are fundamentally limited by representation collapse, a bottleneck that severely degrades long-context performance. We identify that existing approache…
JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search
Dongyun Zou, Zhuoyang Zhang, Junyu Chen +8
We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention vision foundation models while…
ForeAct: Steering Your VLA with Efficient Visual Foresight Planning
Zhuoyang Zhang, Shang Yang, Qinghao Hu +5
Vision-Language-Action (VLA) models convert high-level language instructions into concrete, executable actions, a task that is especially challenging in open-world environments. We…
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
Yecheng Wu, Junyu Chen, Zhuoyang Zhang +7
We introduce DC-AR, a novel masked autoregressive (AR) text-to-image generation framework that delivers superior image generation quality with exceptional computational efficiency.…
Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
Zhuoyang Zhang, Luke J. Huang, Chengyue Wu +4
We present Locality-aware Parallel Decoding (LPD) to accelerate autoregressive image generation. Traditional autoregressive image generation relies on next-patch prediction, a memo…
CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
Qingqing Zhao, Yao Lu, Moo Jin Kim +12
Vision-language-action models (VLAs) have shown potential in leveraging pretrained vision-language models and diverse robot demonstrations for learning generalizable sensorimotor c…
LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
Shang Yang, Junxian Guo, Haotian Tang +7
Large language models (LLMs) have shown remarkable potential in processing long sequences and complex reasoning tasks, yet efficiently serving these models remains challenging due…
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
Enze Xie, Junsong Chen, Junyu Chen +8
We introduce Sana, a text-to-image framework that can efficiently generate images up to 40964096 resolution. Sana can synthesize high-resolution, high-quality images with s…
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
Haotian Tang, Yecheng Wu, Shang Yang +7
We introduce Hybrid Autoregressive Transformer (HART), an autoregressive (AR) visual generation model capable of directly generating 1024x1024 images, rivaling diffusion models in…
COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
Haocheng Xi, Han Cai, Ligeng Zhu +4
FP8 training has emerged as a promising method for improving training efficiency. Existing frameworks accelerate training by applying FP8 computation to linear layers while leaving…
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
Junyu Chen, Han Cai, Junsong Chen +6
We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated…
Wolf: Dense Video Captioning with a World Summarization Framework
Boyi Li, Ligeng Zhu, Ran Tian +20
We propose Wolf, a WOrLd summarization Framework for accurate video captioning. Wolf is an automated captioning framework that adopts a mixture-of-experts approach, leveraging comp…