Recently, model merging techniques have surfaced as a solution to combine multiple single-talent models into a single multi-talent model. However, previous endeavors in this field have either necessitated additional training or fine-tuning processes, or require that the models possess the same pre-trained initialization. In this work, we identify a common drawback in prior works w.r.t. the inconsistency of unit similarity in the weight space and the activation space. To address this inconsistency, we propose an innovative model merging framework, coined as merging under dual-space constraints (MuDSC). Specifically, instead of solely maximizing the objective of a single space, we advocate for the exploration of permutation matrices situated in a region with a unified high similarity in the dual space, achieved through the linear combination of activation and weight similarity matrices. In order to enhance usability, we have also incorporated adaptations for group structure, including Multi-Head Attention and Group Normalization. Comprehensive experimental comparisons demonstrate that MuDSC can significantly boost the performance of merged models with various task combinations and architectures. Furthermore, the visualization of the merged model within the multi-task loss landscape reveals that MuDSC enables the merged model to reside in the overlapping segment, featuring a unified lower loss for each task. Our code is publicly available at https://github.com/zju-vipa/training_free_model_merging.

The last decade has witnessed the success of deep learning and the surge of publicly released trained models, which necessitates the quantification of the model functional distance for various purposes. However, quantifying the model functional distance is always challenging due to the opacity in inner workings and the heterogeneity in architectures or tasks. Inspired by the concept of "field" in physics, in this work we introduce Model Gradient Field (abbr. ModelGiF) to extract homogeneous representations from the heterogeneous pre-trained models. Our main assumption underlying ModelGiF is that each pre-trained deep model uniquely determines a ModelGiF over the input space. The distance between models can thus be measured by the similarity between their ModelGiFs. We validate the effectiveness of the proposed ModelGiF with a suite of testbeds, including task relatedness estimation, intellectual property protection, and model unlearning verification. Experimental results demonstrate the versatility of the proposed ModelGiF on these tasks, with significantly superiority performance to state-of-the-art competitors. Codes are available at https://github.com/zju-vipa/modelgif.

Weight Average (WA) is an active research topic due to its simplicity in ensembling deep networks and the effectiveness in promoting generalization. Existing weight average approaches, however, are often carried out along only one training trajectory in a post-hoc manner (i.e., the weights are averaged after the entire training process is finished), which significantly degrades the diversity between networks and thus impairs the effectiveness. In this paper, inspired by weight average, we propose Lookaround, a straightforward yet effective SGD-based optimizer leading to flatter minima with better generalization. Specifically, Lookaround iterates two steps during the whole training period: the around step and the average step. In each iteration, 1) the around step starts from a common point and trains multiple networks simultaneously, each on transformed data by a different data augmentation, and 2) the average step averages these trained networks to get the averaged network, which serves as the starting point for the next iteration. The around step improves the functionality diversity while the average step guarantees the weight locality of these networks during the whole training, which is essential for WA to work. We theoretically explain the superiority of Lookaround by convergence analysis, and make extensive experiments to evaluate Lookaround on popular benchmarks including CIFAR and ImageNet with both CNNs and ViTs, demonstrating clear superiority over state-of-the-arts. Our code is available at https://github.com/Ardcy/Lookaround.

The initial public offering (IPO) market in Hong Kong is consistently one of the largest in the world. As part of its regulatory responsibilities, Hong Kong Exchanges and Clearing Limited (HKEX) reviews annual reports published by listed companies (issuers). The number of issuers has grown at a fast pace, reaching 2,538 as the end of 2020. This poses a challenge for manually reviewing these annual reports against the many diverse regulatory obligations (listing rules). We propose a system named Jura to improve the efficiency of annual report reviewing with the help of machine learning methods. This system checks the compliance of an issuer's published information against listing rules in four steps: panoptic document recognition, relevant passage location, fine-grained information extraction, and compliance assessment. This paper introduces in detail the passage location step, how it is critical for speeding up compliance assessment, and the various challenges faced. We argue that although a passage is a relatively independent unit, it needs to be combined with document structure and contextual information to accurately locate the relevant passages. With the help of Jura, HKEX reports saving 80% of the time on reviewing issuers' annual reports.

This paper demonstrates a combination of mm- wave low noise amplifier (LNA) and active vector-modulated phase shifter (VMPS) in 40-nm CMOS technology. System considerations of noise and gain are discussed in detail. Wideband impedance conversion is realized through a passive quadrature hybrid coupler (QHC). A three-coil transformer between the variable gain amplifier (VGA) and LNA is utilized to achieve broadband impedance matching, boost transconductance and broaden the bandwidth. With 8-bit resolution, the achieved minimal root-mean-square (RMS) phase and gain errors are 0.26oand 0.48dB, respectively. The overall power consumption is 139.88mW, while the working peak gain is 17.83dB and the minimal NF is 5.4dB. The proposed PS is simulated to work from 22-GHz to 40-GHz, covering the whole Ka-band. The overall area of the LNA-PS is only 0.266 mm2.