Lei Zhao

Wenyi Hong, Weihan Wang, Ming Ding et al.

Beginning with VisualGLM and CogVLM, we are continuously exploring VLMs in pursuit of enhanced vision-language fusion, efficient higher-resolution architecture, and broader modalities and applications. Here we propose the CogVLM2 family, a new generation of visual language models for image and video understanding including CogVLM2, CogVLM2-Video and GLM-4V. As an image understanding model, CogVLM2 inherits the visual expert architecture with improved training recipes in both pre-training and post-training stages, supporting input resolution up to $1344 \times 1344$ pixels. As a video understanding model, CogVLM2-Video integrates multi-frame input with timestamps and proposes automated temporal grounding data construction. Notably, CogVLM2 family has achieved state-of-the-art results on benchmarks like MMBench, MM-Vet, TextVQA, MVBench and VCGBench. All models are open-sourced in https://github.com/THUDM/CogVLM2 and https://github.com/THUDM/GLM-4, contributing to the advancement of the field.

Lei Zhao, Aishwarya Natarajan, Luca Buonanno et al.

Transformer models represent the cutting edge of Deep Neural Networks (DNNs) and excel in a wide range of machine learning tasks. However, processing these models demands significant computational resources and results in a substantial memory footprint. While In-memory Computing (IMC)offers promise for accelerating Vector-Matrix Multiplications(VMMs) with high computational parallelism and minimal data movement, employing it for other crucial DNN operators remains a formidable task. This challenge is exacerbated by the extensive use of complex activation functions, Softmax, and data-dependent matrix multiplications (DMMuls) within Transformer models. To address this challenge, we introduce a Reconfigurable Analog Computing Engine (RACE) by enhancing Analog Content Addressable Memories (ACAMs) to support broader operations. Based on the RACE, we propose the RACE-IT accelerator (meaning RACE for In-memory Transformers) to enable efficient analog-domain execution of all core operations of Transformer models. Given the flexibility of our proposed RACE in supporting arbitrary computations, RACE-IT is well-suited for adapting to emerging and non-traditional DNN architectures without requiring hardware modifications. We compare RACE-IT with various accelerators. Results show that RACE-IT increases performance by 453x and 15x, and reduces energy by 354x and 122x over the state-of-the-art GPUs and existing Transformer-specific IMC accelerators, respectively.

Xingwu Chen, Lei Zhao, Difan Zou

Despite the remarkable success of transformer-based models in various real-world tasks, their underlying mechanisms remain poorly understood. Recent studies have suggested that transformers can implement gradient descent as an in-context learner for linear regression problems and have developed various theoretical analyses accordingly. However, these works mostly focus on the expressive power of transformers by designing specific parameter constructions, lacking a comprehensive understanding of their inherent working mechanisms post-training. In this study, we consider a sparse linear regression problem and investigate how a trained multi-head transformer performs in-context learning. We experimentally discover that the utilization of multi-heads exhibits different patterns across layers: multiple heads are utilized and essential in the first layer, while usually only a single head is sufficient for subsequent layers. We provide a theoretical explanation for this observation: the first layer preprocesses the context data, and the following layers execute simple optimization steps based on the preprocessed context. Moreover, we demonstrate that such a preprocess-then-optimize algorithm can significantly outperform naive gradient descent and ridge regression algorithms. Further experimental results support our explanations. Our findings offer insights into the benefits of multi-head attention and contribute to understanding the more intricate mechanisms hidden within trained transformers.

Junsheng Luan, Guangyuan Li, Lei Zhao et al.

Virtual try-on methods based on diffusion models achieve realistic try-on effects. They use an extra reference network or an additional image encoder to process multiple conditional image inputs, which adds complexity pre-processing and additional computational costs. Besides, they require more than 25 inference steps, bringing longer inference time. In this work, with the development of diffusion transformer (DiT), we rethink the necessity of additional reference network or image encoder and introduce MC-VTON, which leverages DiT's intrinsic backbone to seamlessly integrate minimal conditional try-on inputs. Compared to existing methods, the superiority of MC-VTON is demonstrated in four aspects: (1) Superior detail fidelity. Our DiT-based MC-VTON exhibits superior fidelity in preserving fine-grained details. (2) Simplified network and inputs. We remove any extra reference network or image encoder. We also remove unnecessary conditions like the long prompt, pose estimation, human parsing, and depth map. We require only the masked person image and the garment image. (3) Parameter-efficient training. To process the try-on task, we fine-tune the FLUX.1-dev with only 39.7M additional parameters (0.33% of the backbone parameters). (4) Less inference steps. We apply distillation diffusion on MC-VTON and only need 8 steps to generate a realistic try-on image, with only 86.8M additional parameters (0.72% of the backbone parameters). Experiments show that MC-VTON achieves superior qualitative and quantitative results with fewer condition inputs, trainable parameters, and inference steps than baseline methods.

Dawei Du, Longyin Wen, Pengfei Zhu et al.

Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint. However, there are few algorithms focusing on crowd counting on the drone-captured data due to the lack of comprehensive datasets. To this end, we collect a large-scale dataset and organize the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments in the related fields. The collected dataset is formed by $3,360$ images, including $2,460$ images for training, and $900$ images for testing. Specifically, we manually annotate persons with points in each video frame. There are $14$ algorithms from $15$ institutes submitted to the VisDrone-CC2020 Challenge. We provide a detailed analysis of the evaluation results and conclude the challenge. More information can be found at the website: \url{http://www.aiskyeye.com/}.

Wentao Ouyang, Xiuwu Zhang, Lei Zhao et al.

Click-through rate (CTR) prediction is a critical task in online advertising systems. Existing works mainly address the single-domain CTR prediction problem and model aspects such as feature interaction, user behavior history and contextual information. Nevertheless, ads are usually displayed with natural content, which offers an opportunity for cross-domain CTR prediction. In this paper, we address this problem and leverage auxiliary data from a source domain to improve the CTR prediction performance of a target domain. Our study is based on UC Toutiao (a news feed service integrated with the UC Browser App, serving hundreds of millions of users daily), where the source domain is the news and the target domain is the ad. In order to effectively leverage news data for predicting CTRs of ads, we propose the Mixed Interest Network (MiNet) which jointly models three types of user interest: 1) long-term interest across domains, 2) short-term interest from the source domain and 3) short-term interest in the target domain. MiNet contains two levels of attentions, where the item-level attention can adaptively distill useful information from clicked news / ads and the interest-level attention can adaptively fuse different interest representations. Offline experiments show that MiNet outperforms several state-of-the-art methods for CTR prediction. We have deployed MiNet in UC Toutiao and the A/B test results show that the online CTR is also improved substantially. MiNet now serves the main ad traffic in UC Toutiao.