Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters. Striking a balance between retaining the generalizable representation capacity of the pre-trained model and acquiring task-specific features poses a key challenge. Currently, there is a lack of focus on guiding this delicate trade-off. In this study, we approach the problem from the perspective of Singular Value Decomposition (SVD) of pre-trained parameter matrices, providing insights into the tuning dynamics of existing methods. Building upon this understanding, we propose a Residual-based Low-Rank Rescaling (RLRR) fine-tuning strategy. This strategy not only enhances flexibility in parameter tuning but also ensures that new parameters do not deviate excessively from the pre-trained model through a residual design. Extensive experiments demonstrate that our method achieves competitive performance across various downstream image classification tasks, all while maintaining comparable new parameters. We believe this work takes a step forward in offering a unified perspective for interpreting existing methods and serves as motivation for the development of new approaches that move closer to effectively considering the crucial trade-off mentioned above. Our code is available at \href{https://github.com/zstarN70/RLRR.git}{https://github.com/zstarN70/RLRR.git}.
Language, a prominent human ability to express through sequential symbols, has been computationally mastered by recent advances of large language models (LLMs). By predicting the next word recurrently with huge neural models, LLMs have shown unprecedented capabilities in understanding and reasoning. Circuit, as the "language" of electronic design, specifies the functionality of an electronic device by cascade connections of logic gates. Then, can circuits also be mastered by a a sufficiently large "circuit model", which can conquer electronic design tasks by simply predicting the next logic gate? In this work, we take the first step to explore such possibilities. Two primary barriers impede the straightforward application of LLMs to circuits: their complex, non-sequential structure, and the intolerance of hallucination due to strict constraints (e.g., equivalence). For the first barrier, we encode a circuit as a memory-less, depth-first traversal trajectory, which allows Transformer-based neural models to better leverage its structural information, and predict the next gate on the trajectory as a circuit model. For the second barrier, we introduce an equivalence-preserving decoding process, which ensures that every token in the generated trajectory adheres to the specified equivalence constraints. Moreover, the circuit model can also be regarded as a stochastic policy to tackle optimization-oriented circuit design tasks. Experimentally, we trained a Transformer-based model of 88M parameters, named "Circuit Transformer", which demonstrates impressive performance in end-to-end logic synthesis. With Monte-Carlo tree search, Circuit Transformer significantly improves over resyn2 while retaining strict equivalence, showcasing the potential of generative AI in conquering electronic design challenges.
Low earth orbit (LEO) satellite communications can provide ubiquitous and reliable services, making it an essential part of the Internet of Everything network. Beam hopping (BH) is an emerging technology for effectively addressing the issue of low resource utilization caused by the non-uniform spatio-temporal distribution of traffic demands. However, how to allocate multi-dimensional resources in a timely and efficient way for the highly dynamic LEO satellite systems remains a challenge. This paper proposes a joint beam scheduling and power optimization beam hopping (JBSPO-BH) algorithm considering the differences in the geographic distribution of sink nodes. The JBSPO-BH algorithm decouples the original problem into two sub-problems. The beam scheduling problem is modelled as a potential game, and the Nash equilibrium (NE) point is obtained as the beam scheduling strategy. Moreover, the penalty function interior point method is applied to optimize the power allocation. Simulation results show that the JBSPO-BH algorithm has low time complexity and fast convergence and achieves better performance both in throughput and fairness. Compared with greedy-based BH, greedy-based BH with the power optimization, round-robin BH, Max-SINR BH and satellite resource allocation algorithm, the throughput of the proposed algorithm is improved by 44.99%, 20.79%, 156.06%, 15.39% and 8.17%, respectively.
Identity-consistent video generation seeks to synthesize videos that are guided by both textual prompts and reference images of entities. Current approaches typically utilize cross-attention layers to integrate the appearance of the entity, which predominantly captures semantic attributes, resulting in compromised fidelity of entities. Moreover, these methods necessitate iterative fine-tuning for each new entity encountered, thereby limiting their applicability. To address these challenges, we introduce VideoAssembler, a novel end-to-end framework for identity-consistent video generation that can conduct inference directly when encountering new entities. VideoAssembler is adept at producing videos that are not only flexible with respect to the input reference entities but also responsive to textual conditions. Additionally, by modulating the quantity of input images for the entity, VideoAssembler enables the execution of tasks ranging from image-to-video generation to sophisticated video editing. VideoAssembler comprises two principal components: the Reference Entity Pyramid (REP) encoder and the Entity-Prompt Attention Fusion (EPAF) module. The REP encoder is designed to infuse comprehensive appearance details into the denoising stages of the stable diffusion model. Concurrently, the EPAF module is utilized to integrate text-aligned features effectively. Furthermore, to mitigate the challenge of scarce data, we present a methodology for the preprocessing of training data. Our evaluation of the VideoAssembler framework on the UCF-101, MSR-VTT, and DAVIS datasets indicates that it achieves good performances in both quantitative and qualitative analyses (346.84 in FVD and 48.01 in IS on UCF-101). Our project page is at https://gulucaptain.github.io/videoassembler/.
Federated learning effectively addresses issues such as data privacy by collaborating across participating devices to train global models. However, factors such as network topology and device computing power can affect its training or communication process in complex network environments. A new network architecture and paradigm with computing-measurable, perceptible, distributable, dispatchable, and manageable capabilities, computing and network convergence (CNC) of 6G networks can effectively support federated learning training and improve its communication efficiency. By guiding the participating devices' training in federated learning based on business requirements, resource load, network conditions, and arithmetic power of devices, CNC can reach this goal. In this paper, to improve the communication efficiency of federated learning in complex networks, we study the communication efficiency optimization of federated learning for computing and network convergence of 6G networks, methods that gives decisions on its training process for different network conditions and arithmetic power of participating devices in federated learning. The experiments address two architectures that exist for devices in federated learning and arrange devices to participate in training based on arithmetic power while achieving optimization of communication efficiency in the process of transferring model parameters. The results show that the method we proposed can (1) cope well with complex network situations (2) effectively balance the delay distribution of participating devices for local training (3) improve the communication efficiency during the transfer of model parameters (4) improve the resource utilization in the network.
Latent Diffusion Models (LDMs) are renowned for their powerful capabilities in image and video synthesis. Yet, video editing methods suffer from insufficient pre-training data or video-by-video re-training cost. In addressing this gap, we propose FLDM (Fused Latent Diffusion Model), a training-free framework to achieve text-guided video editing by applying off-the-shelf image editing methods in video LDMs. Specifically, FLDM fuses latents from an image LDM and an video LDM during the denoising process. In this way, temporal consistency can be kept with video LDM while high-fidelity from the image LDM can also be exploited. Meanwhile, FLDM possesses high flexibility since both image LDM and video LDM can be replaced so advanced image editing methods such as InstructPix2Pix and ControlNet can be exploited. To the best of our knowledge, FLDM is the first method to adapt off-the-shelf image editing methods into video LDMs for video editing. Extensive quantitative and qualitative experiments demonstrate that FLDM can improve the textual alignment and temporal consistency of edited videos.
Inspired by the remarkable success of Latent Diffusion Models (LDMs) for image synthesis, we study LDM for text-to-video generation, which is a formidable challenge due to the computational and memory constraints during both model training and inference. A single LDM is usually only capable of generating a very limited number of video frames. Some existing works focus on separate prediction models for generating more video frames, which suffer from additional training cost and frame-level jittering, however. In this paper, we propose a framework called "Reuse and Diffuse" dubbed $\textit{VidRD}$ to produce more frames following the frames already generated by an LDM. Conditioned on an initial video clip with a small number of frames, additional frames are iteratively generated by reusing the original latent features and following the previous diffusion process. Besides, for the autoencoder used for translation between pixel space and latent space, we inject temporal layers into its decoder and fine-tune these layers for higher temporal consistency. We also propose a set of strategies for composing video-text data that involve diverse content from multiple existing datasets including video datasets for action recognition and image-text datasets. Extensive experiments show that our method achieves good results in both quantitative and qualitative evaluations. Our project page is available $\href{https://anonymous0x233.github.io/ReuseAndDiffuse/}{here}$.
Removing degradation from document images not only improves their visual quality and readability, but also enhances the performance of numerous automated document analysis and recognition tasks. However, existing regression-based methods optimized for pixel-level distortion reduction tend to suffer from significant loss of high-frequency information, leading to distorted and blurred text edges. To compensate for this major deficiency, we propose DocDiff, the first diffusion-based framework specifically designed for diverse challenging document enhancement problems, including document deblurring, denoising, and removal of watermarks and seals. DocDiff consists of two modules: the Coarse Predictor (CP), which is responsible for recovering the primary low-frequency content, and the High-Frequency Residual Refinement (HRR) module, which adopts the diffusion models to predict the residual (high-frequency information, including text edges), between the ground-truth and the CP-predicted image. DocDiff is a compact and computationally efficient model that benefits from a well-designed network architecture, an optimized training loss objective, and a deterministic sampling process with short time steps. Extensive experiments demonstrate that DocDiff achieves state-of-the-art (SOTA) performance on multiple benchmark datasets, and can significantly enhance the readability and recognizability of degraded document images. Furthermore, our proposed HRR module in pre-trained DocDiff is plug-and-play and ready-to-use, with only 4.17M parameters. It greatly sharpens the text edges generated by SOTA deblurring methods without additional joint training. Available codes: https://github.com/Royalvice/DocDiff
Quantization plays a critical role in digital signal processing systems, allowing the representation of continuous amplitude signals with a finite number of bits. However, accurately representing signals requires a large number of quantization bits, which causes severe cost, power consumption, and memory burden. A promising way to address this issue is task-based quantization. By exploiting the task information for the overall system design, task-based quantization can achieve satisfying performance with low quantization costs. In this work, we apply task-based quantization to multi-user signal recovery and present a hardware prototype implementation. The prototype consists of a tailored configurable combining board, and a software-based processing and demonstration system. Through experiments, we verify that with proper design, the task-based quantization achieves a reduction of 25 fold in memory by reducing from 16 receivers with 16 bits each to 2 receivers with 5 bits each, without compromising signal recovery performance.