37 citations · 102 across the 16 of their papers we have counts for
17 papers
Distance-KV: Exploiting Relative Distance for Efficient Long-Context Inference
Xianpeng Shang, Canbin Huang, Jiang Li +4
The memory usage and decoding latency of LLM inference grow rapidly with context length. To reduce these costs, key-value (KV) cache compression methods selectively retain cached s…
Training-Inference Consistent Segmented Execution for Long-Context LLMs
Xianpeng Shang, Jiang Li, Zehua Duo +2
Transformer-based large language models face severe scalability challenges in long-context generation due to the computational and memory costs of full-context attention. Under pra…
HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
Qi Cai, Jingwen Chen, Chengmin Gao +22
The evolution of visual generative models has long been constrained by fragmented architectures relying on disjoint text encoders and external VAEs. In this report, we present HiDr…
Visual Autoregressive Modeling for Instruction-Guided Image Editing
Qingyang Mao, Qi Cai, Yehao Li +5
Recent advances in diffusion models have brought remarkable visual fidelity to instruction-guided image editing. However, their global denoising process inherently entangles the ed…
Creatively Upscaling Images with Global-Regional Priors
Yurui Qian, Qi Cai, Yingwei Pan +2
Contemporary diffusion models show remarkable capability in text-to-image generation, while still being limited to restricted resolutions (e.g., 1,024 X 1,024). Recent advances ena…
Boosting Diffusion Models with Moving Average Sampling in Frequency Domain
Yurui Qian, Qi Cai, Yingwei Pan +4
Diffusion models have recently brought a powerful revolution in image generation. Despite showing impressive generative capabilities, most of these models rely on the current sampl…
3D Cascade RCNN: High Quality Object Detection in Point Clouds
Qi Cai, Yingwei Pan, Ting Yao +1
Recent progress on 2D object detection has featured Cascade RCNN, which capitalizes on a sequence of cascade detectors to progressively improve proposal quality, towards high-quali…
Out-of-Distribution Detection with Hilbert-Schmidt Independence Optimization
Jingyang Lin, Yu Wang, Qi Cai +4
Outlier detection tasks have been playing a critical role in AI safety. There has been a great challenge to deal with this task. Observations show that deep neural network classifi…
Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation
Yingwei Pan, Yehao Li, Yiheng Zhang +5
This paper presents an overview and comparative analysis of our systems designed for the following two tracks in SAPIEN ManiSkill Challenge 2021: No Interaction Track: The No Inter…
A Low Rank Promoting Prior for Unsupervised Contrastive Learning
Yu Wang, Jingyang Lin, Qi Cai +4
Unsupervised learning is just at a tipping point where it could really take off. Among these approaches, contrastive learning has seen tremendous progress and led to state-of-the-a…
Joint Contrastive Learning with Infinite Possibilities
Qi Cai, Yu Wang, Yingwei Pan +2
This paper explores useful modifications of the recent development in contrastive learning via novel probabilistic modeling. We derive a particular form of contrastive loss named J…
Learning a Unified Sample Weighting Network for Object Detection
Qi Cai, Yingwei Pan, Yu Wang +3
Region sampling or weighting is significantly important to the success of modern region-based object detectors. Unlike some previous works, which only focus on "hard" samples when…
Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019
Yingwei Pan, Yehao Li, Qi Cai +2
This notebook paper presents an overview and comparative analysis of our systems designed for the following two tasks in Visual Domain Adaptation Challenge (VisDA-2019): multi-sour…
vireoJD-MM at Activity Detection in Extended Videos
Fuchen Long, Qi Cai, Zhaofan Qiu +4
This notebook paper presents an overview and comparative analysis of our system designed for activity detection in extended videos (ActEV-PC) in ActivityNet Challenge 2019. Specifi…
Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019
Zhaofan Qiu, Dong Li, Yehao Li +3
This notebook paper presents an overview and comparative analysis of our systems designed for the following three tasks in ActivityNet Challenge 2019: trimmed action recognition, d…
Exploring Object Relation in Mean Teacher for Cross-Domain Detection
Qi Cai, Yingwei Pan, Chong-Wah Ngo +3
Rendering synthetic data (e.g., 3D CAD-rendered images) to generate annotations for learning deep models in vision tasks has attracted increasing attention in recent years. However…
Memory Matching Networks for One-Shot Image Recognition
Qi Cai, Yingwei Pan, Ting Yao +2
In this paper, we introduce the new ideas of augmenting Convolutional Neural Networks (CNNs) with Memory and learning to learn the network parameters for the unlabelled images on t…