39 citations · 92 across the 11 of their papers we have counts for
11 papers
PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models
Bin Hu, Yanwen Ma, Jiehui Huang +14
Recent game world models can synthesize visually plausible, action-conditioned rollouts. However, their interaction behaviors often remain limited to exploratory or wandering traje…
Prompt Highlighter: Interactive Control for Multi-Modal LLMs
Yuechen Zhang, Shengju Qian, Bohao Peng +2
This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation. Multi-modal LLMs empower multi-modality understanding with t…
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
Yukang Chen, Shengju Qian, Haotian Tang +4
We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost. Typically, trainin…
TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation
Jingyao Li, Pengguang Chen, Shengju Qian +2
Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patc…
StraIT: Non-autoregressive Generation with Stratified Image Transformer
Shengju Qian, Huiwen Chang, Yuanzhen Li +3
We propose Stratified Image Transformer(StraIT), a pure non-autoregressive(NAR) generative model that demonstrates superiority in high-quality image synthesis over existing autoreg…
What Makes for Good Tokenizers in Vision Transformer?
Shengju Qian, Yi Zhu, Wenbo Li +2
The architecture of transformers, which recently witness booming applications in vision tasks, has pivoted against the widespread convolutional paradigm. Relying on the tokenizatio…
On Efficient Transformer-Based Image Pre-training for Low-Level Vision
Wenbo Li, Xin Lu, Shengju Qian +3
Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing sy…
Blending Anti-Aliasing into Vision Transformer
Shengju Qian, Hao Shao, Yi Zhu +2
The transformer architectures, based on self-attention mechanism and convolution-free design, recently found superior performance and booming applications in computer vision. Howev…
Temporal Interlacing Network
Hao Shao, Shengju Qian, Yu Liu
For a long time, the vision community tries to learn the spatio-temporal representation by combining convolutional neural network together with various temporal models, such as the…
Make a Face: Towards Arbitrary High Fidelity Face Manipulation
Shengju Qian, Kwan-Yee Lin, Wayne Wu +5
Recent studies have shown remarkable success in face manipulation task with the advance of GANs and VAEs paradigms, but the outputs are sometimes limited to low-resolution and lack…
Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation
Shengju Qian, Keqiang Sun, Wayne Wu +2
Facial landmark detection, or face alignment, is a fundamental task that has been extensively studied. In this paper, we investigate a new perspective of facial landmark detection…