We propose a generative model that, given a coarsely edited image, synthesizes a photorealistic output that follows the prescribed layout. Our method transfers fine details from the original image and preserves the identity of its parts. Yet, it adapts it to the lighting and context defined by the new layout. Our key insight is that videos are a powerful source of supervision for this task: objects and camera motions provide many observations of how the world changes with viewpoint, lighting, and physical interactions. We construct an image dataset in which each sample is a pair of source and target frames extracted from the same video at randomly chosen time intervals. We warp the source frame toward the target using two motion models that mimic the expected test-time user edits. We supervise our model to translate the warped image into the ground truth, starting from a pretrained diffusion model. Our model design explicitly enables fine detail transfer from the source frame to the generated image, while closely following the user-specified layout. We show that by using simple segmentations and coarse 2D manipulations, we can synthesize a photorealistic edit faithful to the user's input while addressing second-order effects like harmonizing the lighting and physical interactions between edited objects.
Creating content for a specific identity (ID) has shown significant interest in the field of generative models. In the field of text-to-image generation (T2I), subject-driven content generation has achieved great progress with the ID in the images controllable. However, extending it to video generation is not well explored. In this work, we propose a simple yet effective subject identity controllable video generation framework, termed Video Custom Diffusion (VCD). With a specified subject ID defined by a few images, VCD reinforces the identity information extraction and injects frame-wise correlation at the initialization stage for stable video outputs with identity preserved to a large extent. To achieve this, we propose three novel components that are essential for high-quality ID preservation: 1) an ID module trained with the cropped identity by prompt-to-segmentation to disentangle the ID information and the background noise for more accurate ID token learning; 2) a text-to-video (T2V) VCD module with 3D Gaussian Noise Prior for better inter-frame consistency and 3) video-to-video (V2V) Face VCD and Tiled VCD modules to deblur the face and upscale the video for higher resolution. Despite its simplicity, we conducted extensive experiments to verify that VCD is able to generate stable and high-quality videos with better ID over the selected strong baselines. Besides, due to the transferability of the ID module, VCD is also working well with finetuned text-to-image models available publically, further improving its usability. The codes are available at https://github.com/Zhen-Dong/Magic-Me.
Single-modal object re-identification (ReID) faces great challenges in maintaining robustness within complex visual scenarios. In contrast, multi-modal object ReID utilizes complementary information from diverse modalities, showing great potentials for practical applications. However, previous methods may be easily affected by irrelevant backgrounds and usually ignore the modality gaps. To address above issues, we propose a novel learning framework named \textbf{EDITOR} to select diverse tokens from vision Transformers for multi-modal object ReID. We begin with a shared vision Transformer to extract tokenized features from different input modalities. Then, we introduce a Spatial-Frequency Token Selection (SFTS) module to adaptively select object-centric tokens with both spatial and frequency information. Afterwards, we employ a Hierarchical Masked Aggregation (HMA) module to facilitate feature interactions within and across modalities. Finally, to further reduce the effect of backgrounds, we propose a Background Consistency Constraint (BCC) and an Object-Centric Feature Refinement (OCFR). They are formulated as two new loss functions, which improve the feature discrimination with background suppression. As a result, our framework can generate more discriminative features for multi-modal object ReID. Extensive experiments on three multi-modal ReID benchmarks verify the effectiveness of our methods. The code is available at https://github.com/924973292/EDITOR.
Text documents, including programs, typically have human-readable semantic structure. Historically, programmatic access to these semantics has required explicit in-document tagging. Especially in systems where the text has an execution semantics, this means it is an opt-in feature that is hard to support properly. Today, language models offer a new method: metadata can be bound to entities in changing text using a model's human-like understanding of semantics, with no requirements on the document structure. This method expands the applications of document annotation, a fundamental operation in program writing, debugging, maintenance, and presentation. We contribute a system that employs an intelligent agent to re-tag modified programs, enabling rich annotations to automatically follow code as it evolves. We also contribute a formal problem definition, an empirical synthetic benchmark suite, and our benchmark generator. Our system achieves an accuracy of 90% on our benchmarks and can replace a document's tags in parallel at a rate of 5 seconds per tag. While there remains significant room for improvement, we find performance reliable enough to justify further exploration of applications.
The deliberate manipulation of ammonium persulfate, methylenebisacrylamide, dimethyleacrylamide, and polyethylene oxide concentrations resulted in the development of a hydrogel with an exceptional stretchability, capable of extending up to 260 times its original length. This study aims to elucidate the molecular architecture underlying this unique phenomenon by exploring potential reaction mechanisms, facilitated by an artificial intelligence prediction system. Artificial intelligence predictor introduces a novel approach to interlinking two polymers, involving the formation of networks interconnected with linear chains following random chain scission. This novel configuration leads to the emergence of a distinct type of hydrogel, herein referred to as a "Span Network." Additionally, Fourier-transform infrared spectroscopy (FTIR) is used to investigate functional groups that may be implicated in the proposed mechanism, with ester formation confirmed among numerous hydroxyl end groups obtained from chain scission of PEO and carboxyl groups formed on hydrogel networks.
Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is attention distillation, which uses attention scores as a supervision signal instead of manually annotated query-document pairs. Despite its growing popularity, the detailed mechanisms behind the success of attention distillation remain unexplored, particularly the specific patterns it leverages to benefit training. In this paper, we address this gap by conducting a comprehensive review of attention distillation workflow and identifying key factors influencing the learning quality of retrieval-augmented language models. We further propose indicators for optimizing models' training methods and avoiding ineffective training.
This paper presents three established theories of human decision-making and describes how they can be integrated to provide a model of purposive human action. Taking seriously the idea of language as action the model is then applied to the conversational user interfaces. Theory based AI research has had a hard time recently and the aim here is to revitalise interest in understanding what LLMs are actually doing other than running poorly understood machine learning routines over all the data the relevant Big Tech company can hoover up. When a raspberry pi computer for under 50USD is up to 400 times faster than the first commercial Cray super computer~\cite{crayVpi}, Big Tech can get really close to having an infinite number of monkeys typing at random and producing text, some of which will make sense. By understanding where ChatGPT's apparent intelligence comes from, perhaps we can perform the magic with fewer resources and at the same time gain some understanding about our relationship with our world.
Current advancements in technology have focused the attention of the quantum computing community toward exploring the potential of near-term devices whose computing power surpasses that of classical computers in practical applications. An unresolved central question revolves around whether the inherent noise in these devices can be overcome or whether any potential quantum advantage would be limited. There is no doubt that crosstalk is one of the main sources of noise in noisy intermediate-scale quantum (NISQ) systems, and it poses a fundamental challenge to hardware designs. Crosstalk between parallel instructions can corrupt quantum states and cause incorrect program execution. In this study, we present a comprehensive analysis of the crosstalk error effect on NISQ computers. Our approach is extremely straightforward and practical for characterizing the crosstalk error of various multi-qubit devices. In particular, we combine the randomized benchmarking (RB) and simultaneous randomized benchmarking (SRB) protocol to characterize the crosstalk error from the correlation controlled-NOT (CNOT) gate. We demonstrate this protocol experimentally on 5- \& 7-qubit devices. Our results demonstrate the crosstalk error model of two different IBM quantum devices over the experimental week and compare the error variation against the machine, number of qubits, quantum volume, processor, and topology of the IBM quantum devices. We then confirm the improvement in the circuit fidelity on different benchmarks by up to 3.06x via inserting an instruction barrier, as compared with an IBM quantum noisy device which offers near-optimal crosstalk mitigation in practice. Most importantly, we provide insight to ensure that the quantum operation can perform its quantum magic undisturbed.
We study the effect of the batch size to the total gradient variance in differentially private stochastic gradient descent (DP-SGD), seeking a theoretical explanation for the usefulness of large batch sizes. As DP-SGD is the basis of modern DP deep learning, its properties have been widely studied, and recent works have empirically found large batch sizes to be beneficial. However, theoretical explanations of this benefit are currently heuristic at best. We first observe that the total gradient variance in DP-SGD can be decomposed into subsampling-induced and noise-induced variances. We then prove that in the limit of an infinite number of iterations, the effective noise-induced variance is invariant to the batch size. The remaining subsampling-induced variance decreases with larger batch sizes, so large batches reduce the effective total gradient variance. We confirm numerically that the asymptotic regime is relevant in practical settings when the batch size is not small, and find that outside the asymptotic regime, the total gradient variance decreases even more with large batch sizes. We also find a sufficient condition that implies that large batch sizes similarly reduce effective DP noise variance for one iteration of DP-SGD.
Accurate robotic control over interactions with the environment is fundamentally grounded in understanding tactile contacts. In this paper, we introduce MagicTac, a novel high-resolution grid-based tactile sensor. This sensor employs a 3D multi-layer grid-based design, inspired by the Magic Cube structure. This structure can help increase the spatial resolution of MagicTac to perceive external interaction contacts. Moreover, the sensor is produced using the multi-material additive manufacturing technique, which simplifies the manufacturing process while ensuring repeatability of production. Compared to traditional vision-based tactile sensors, it offers the advantages of i) high spatial resolution, ii) significant affordability, and iii) fabrication-friendly construction that requires minimal assembly skills. We evaluated the proposed MagicTac in the tactile reconstruction task using the deformation field and optical flow. Results indicated that MagicTac could capture fine textures and is sensitive to dynamic contact information. Through the grid-based multi-material additive manufacturing technique, the affordability and productivity of MagicTac can be enhanced with a minimum manufacturing cost of 4.76 GBP and a minimum manufacturing time of 24.6 minutes.