arXiv subjects

Zhen Zhu

Publications and source records attributed to Zhen Zhu.

At least 37 records · Page 2Linked to original sources

arXiv2025

InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow

We propose a fast text-guided image editing method called InstantEdit based on the RectifiedFlow framework, which is structured as a few-step editing process that preserves critical content while following closely to textual instructions. Our approach leverages the straight sampling trajectories of RectifiedFlow by introducing a specialized inversion strategy called PerRFI. To maintain consistent while editable results for RectifiedFlow model, we further propose a novel regeneration method, Inversion Latent Injection, which effectively reuses latent information obtained during inversion to facilitate more coherent and detailed regeneration. Additionally, we propose a Disentangled Prompt Guidance technique to balance editability with detail preservation, and integrate a Canny-conditioned ControlNet to incorporate structural cues and suppress artifacts. Evaluation on the PIE image editing dataset demonstrates that InstantEdit is not only fast but also achieves better qualitative and quantitative results compared to state-of-the-art few-step editing methods.

cs.CV↗

arXiv2025

Training-free Geometric Image Editing on Diffusion Models

We tackle the task of geometric image editing, where an object within an image is repositioned, reoriented, or reshaped while preserving overall scene coherence. Previous diffusion-based editing methods often attempt to handle all relevant subtasks in a single step, proving difficult when transformations become large or structurally complex. We address this by proposing a decoupled pipeline that separates object transformation, source region inpainting, and target region refinement. Both inpainting and refinement are implemented using a training-free diffusion approach, FreeFine. In experiments on our new GeoBench benchmark, which contains both 2D and 3D editing scenarios, FreeFine outperforms state-of-the-art alternatives in image fidelity, and edit precision, especially under demanding transformations. Code and benchmark are available at: https://github.com/CIawevy/FreeFine

cs.CV↗

arXiv2025

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learning (RL) unlocks a new axis for the continued improvement of artificial intelligence, with the promise that large language models (LLMs) can scale their training data by learning to explore with rewards. However, prior published work has not produced competitive results. In light of this, we report on the training practice of Kimi k1.5, our latest multi-modal LLM trained with RL, including its RL training techniques, multi-modal data recipes, and infrastructure optimization. Long context scaling and improved policy optimization methods are key ingredients of our approach, which establishes a simplistic, effective RL framework without relying on more complex techniques such as Monte Carlo tree search, value functions, and process reward models. Notably, our system achieves state-of-the-art reasoning performance across multiple benchmarks and modalities -- e.g., 77.5 on AIME, 96.2 on MATH 500, 94-th percentile on Codeforces, 74.9 on MathVista -- matching OpenAI's o1. Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e.g., 60.8 on AIME, 94.6 on MATH500, 47.3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3.5 by a large margin (up to +550%).

cs.AI↗

arXiv2025

Zero-Shot Low Light Image Enhancement with Diffusion Prior

In this paper, we present a simple yet highly effective "free lunch" solution for low-light image enhancement (LLIE), which aims to restore low-light images as if acquired in well-illuminated environments. Our method necessitates no optimization, training, fine-tuning, text conditioning, or hyperparameter adjustments, yet it consistently reconstructs low-light images with superior fidelity. Specifically, we leverage a pre-trained text-to-image diffusion prior, learned from training on a large collection of natural images, and the features present in the model itself to guide the inference, in contrast to existing methods that depend on customized constraints. Comprehensive quantitative evaluations demonstrate that our approach outperforms SOTA methods on established datasets, while qualitative analyses indicate enhanced color accuracy and the rectification of subtle chromatic deviations. Furthermore, additional experiments reveal that our method, without any modifications, achieves SOTA-comparable performance in the auto white balance (AWB) task.

cs.CV↗

arXiv2025

AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models

Training and deploying reinforcement learning (RL) policies for robots, especially in accomplishing specific tasks, presents substantial challenges. Recent advancements have explored diverse reward function designs, training techniques, simulation-to-reality (sim-to-real) transfers, and performance analysis methodologies, yet these still require significant human intervention. This paper introduces an end-to-end framework for training and deploying RL policies, guided by Large Language Models (LLMs), and evaluates its effectiveness on bipedal robots. The framework consists of three interconnected modules: an LLM-guided reward function design module, an RL training module leveraging prior work, and a sim-to-real homomorphic evaluation module. This design significantly reduces the need for human input by utilizing only essential simulation and deployment platforms, with the option to incorporate human-engineered strategies and historical data. We detail the construction of these modules, their advantages over traditional approaches, and demonstrate the framework's capability to autonomously develop and refine controlling strategies for bipedal robot locomotion, showcasing its potential to operate independently of human intervention.

cs.RO↗

arXiv2024

ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks

"A data scientist is tasked with developing a low-cost surgical VQA system for a 2-month workshop. Due to data sensitivity, she collects 50 hours of surgical video from a hospital, requiring two months for privacy approvals. Privacy restrictions prevent uploading data to platforms like ChatGPT, so she assembles one annotator and a medical expert to manually create QA pairs. This process takes three weeks and costs over $10,000. The trained model provides accurate responses within the limited data scope but lacks broader generalizability, completing the project in 3 months." To simplify the challenges presented in the scenario above. In this paper, we replace the image input with text for Vision-language training. Inspired by prior noise injection methods to reduce modality gaps, we introduce Adaptive ranged cosine Similarity injected noise (ArcSin). First, we introduce an innovative adaptive noise scale that effectively generates the textual elements with more variability while preserving the original text feature's integrity. Second, a similarity pool strategy is employed, expanding the domain generalization potential by broadening the overall noise scale. This dual strategy effectively broadens the scope of the original domain while safeguarding content integrity. Our empirical results demonstrate that these models closely rival those trained on images in terms of performance. Specifically, our method exhibits substantial improvements over the previous state-of-the-art, achieving gains of 1.9 and 1.1 CIDEr points in S-Cap and M-Cap, respectively. Additionally, we observe increases of 0.5 percentage points (pp), 1.4 pp, and 1.4 pp in accuracy for VQA, VQA-E, and VE, respectively, pushing the boundaries of what is achievable within the constraints of image-trained model benchmarks.

cs.CV↗

arXiv2024

Continual Learning in Open-vocabulary Classification with Complementary Memory Systems

We introduce a method for flexible and efficient continual learning in open-vocabulary image classification, drawing inspiration from the complementary learning systems observed in human cognition. Specifically, we propose to combine predictions from a CLIP zero-shot model and the exemplar-based model, using the zero-shot estimated probability that a sample's class is within the exemplar classes. We also propose a "tree probe" method, an adaption of lazy learning principles, which enables fast learning from new examples with competitive accuracy to batch-trained linear models. We test in data incremental, class incremental, and task incremental settings, as well as ability to perform flexible inference on varying subsets of zero-shot and learned categories. Our proposed method achieves a good balance of learning speed, target task effectiveness, and zero-shot effectiveness. Code will be available at https://github.com/jessemelpolio/TreeProbe.

cs.CV↗

arXiv2024

Anytime Continual Learning for Open Vocabulary Classification

We propose an approach for anytime continual learning (AnytimeCL) for open vocabulary image classification. The AnytimeCL problem aims to break away from batch training and rigid models by requiring that a system can predict any set of labels at any time and efficiently update and improve when receiving one or more training samples at any time. Despite the challenging goal, we achieve substantial improvements over recent methods. We propose a dynamic weighting between predictions of a partially fine-tuned model and a fixed open vocabulary model that enables continual improvement when training samples are available for a subset of a task's labels. We also propose an attention-weighted PCA compression of training features that reduces storage and computation with little impact to model accuracy. Our methods are validated with experiments that test flexibility of learning and inference. Code is available at https://github.com/jessemelpolio/AnytimeCL.

cs.CV↗

arXiv2024

Undergraduate Robotics Education with General Instructors using a Student-Centered Personalized Learning Framework

Recent advancements in robotics, including applications like self-driving cars, unmanned systems, and medical robots, have had a significant impact on the job market. On one hand, big robotics companies offer training programs based on the job requirements. However, these training programs may not be as beneficial as general robotics programs offered by universities or community colleges. On the other hand, community colleges and universities face challenges with required resources, especially qualified instructors, to offer students advanced robotics education. Furthermore, the diverse backgrounds of undergraduate students present additional challenges. Some students bring extensive industry experiences, while others are newcomers to the field. To address these challenges, we propose a student-centered personalized learning framework for robotics. This framework allows a general instructor to teach undergraduate-level robotics courses by breaking down course topics into smaller components with well-defined topic dependencies, structured as a graph. This modular approach enables students to choose their learning path, catering to their unique preferences and pace. Moreover, our framework's flexibility allows for easy customization of teaching materials to meet the specific needs of host institutions. In addition to teaching materials, a frequently-asked-questions document would be prepared for a general instructor. If students' robotics questions cannot be answered by the instructor, the answers to these questions may be included in this document. For questions not covered in this document, we can gather and address them through collaboration with the robotics community and course content creators. Our user study results demonstrate the promise of this method in delivering undergraduate-level robotics education tailored to individual learning outcomes and preferences.

cs.RO↗

arXiv2024

Social Media Perceptions of 51% Attacks on Proof-of-Work Cryptocurrencies: A Natural Language Processing Approach

This work is the first study on the effects of attacks on cryptocurrencies as expressed in the sentiments and emotions of social media users. Our goals are to design the methodologies for the study including data collection, conduct volumetric and temporal analyses of the data, and profile the sentiments and emotions that emerge from the data. As a first step, we have created a first-of-its-kind comprehensive list of 31 events of 51% attacks on various PoW cryptocurrencies, showing that these events are quite common contrary to the general perception. We have gathered Twitter data on the events as well as benchmark data during normal times for comparison. We have defined parameters for profiling the datasets based on their sentiments and emotions. We have studied the variation of these sentiment and emotion profiles when a cryptocurrency is under attack and the benchmark otherwise, between multiple attack events of the same cryptocurrency, and between different cryptocurrencies. Our results confirm some expected overall behaviour and reactions while providing nuanced insights that may not be obvious or may even be considered surprising. Our code and datasets are publicly accessible.

cs.SI↗

arXiv2023

Survey on Memory-Augmented Neural Networks: Cognitive Insights to AI Applications

This paper explores Memory-Augmented Neural Networks (MANNs), delving into how they blend human-like memory processes into AI. It covers different memory types, like sensory, short-term, and long-term memory, linking psychological theories with AI applications. The study investigates advanced architectures such as Hopfield Networks, Neural Turing Machines, Correlation Matrix Memories, Memformer, and Neural Attention Memory, explaining how they work and where they excel. It dives into real-world uses of MANNs across Natural Language Processing, Computer Vision, Multimodal Learning, and Retrieval Models, showing how memory boosters enhance accuracy, efficiency, and reliability in AI tasks. Overall, this survey provides a comprehensive view of MANNs, offering insights for future research in memory-based AI systems.

cs.AI↗

arXiv2023

SingleInsert: Inserting New Concepts from a Single Image into Text-to-Image Models for Flexible Editing

Recent progress in text-to-image (T2I) models enables high-quality image generation with flexible textual control. To utilize the abundant visual priors in the off-the-shelf T2I models, a series of methods try to invert an image to proper embedding that aligns with the semantic space of the T2I model. However, these image-to-text (I2T) inversion methods typically need multiple source images containing the same concept or struggle with the imbalance between editing flexibility and visual fidelity. In this work, we point out that the critical problem lies in the foreground-background entanglement when learning an intended concept, and propose a simple and effective baseline for single-image I2T inversion, named SingleInsert. SingleInsert adopts a two-stage scheme. In the first stage, we regulate the learned embedding to concentrate on the foreground area without being associated with the irrelevant background. In the second stage, we finetune the T2I model for better visual resemblance and devise a semantic loss to prevent the language drift problem. With the proposed techniques, SingleInsert excels in single concept generation with high visual fidelity while allowing flexible editing. Additionally, SingleInsert can perform single-image novel view synthesis and multiple concepts composition without requiring joint training. To facilitate evaluation, we design an editing prompt list and introduce a metric named Editing Success Rate (ESR) for quantitative assessment of editing flexibility. Our project page is: https://jarrentwu1031.github.io/SingleInsert-web/

cs.CV↗

arXiv2023

Learning in a Single Domain for Non-Stationary Multi-Texture Synthesis

This paper aims for a new generation task: non-stationary multi-texture synthesis, which unifies synthesizing multiple non-stationary textures in a single model. Most non-stationary textures have large scale variance and can hardly be synthesized through one model. To combat this, we propose a multi-scale generator to capture structural patterns of various scales and effectively synthesize textures with a minor cost. However, it is still hard to handle textures of different categories with different texture patterns. Therefore, we present a category-specific training strategy to focus on learning texture pattern of a specific domain. Interestingly, once trained, our model is able to produce multi-pattern generations with dynamic variations without the need to finetune the model for different styles. Moreover, an objective evaluation metric is designed for evaluating the quality of texture expansion and global structure consistency. To our knowledge, ours is the first scheme for this challenging task, including model, training, and evaluation. Experimental results demonstrate the proposed method achieves superior performance and time efficiency. The code will be available after the publication.

cs.CV↗

arXiv2023

Consistent Multimodal Generation via A Unified GAN Framework

We investigate how to generate multimodal image outputs, such as RGB, depth, and surface normals, with a single generative model. The challenge is to produce outputs that are realistic, and also consistent with each other. Our solution builds on the StyleGAN3 architecture, with a shared backbone and modality-specific branches in the last layers of the synthesis network, and we propose per-modality fidelity discriminators and a cross-modality consistency discriminator. In experiments on the Stanford2D3D dataset, we demonstrate realistic and consistent generation of RGB, depth, and normal images. We also show a training recipe to easily extend our pretrained model on a new domain, even with a few pairwise data. We further evaluate the use of synthetically generated RGB and depth pairs for training or fine-tuning depth estimators. Code will be available at https://github.com/jessemelpolio/MultimodalGAN.

cs.CV↗

arXiv2022

A Weighted and Normalized Gould-Fernandez brokerage measure

The Gould and Fernandez local brokerage measure defines brokering roles based on the group membership of the nodes from the incoming and outgoing edges. This paper extends on this brokerage measure to account for weighted edges and introduces the Weighted-Normalized Gould-Fernandez measure (WNGF). The value added of this new measure is demonstrated empirically with both a macro level trade network and a micro level organization network. The measure is first applied to the EUREGIO inter-regional trade dataset and then to an organizational network in a research and development group. The results gained from the WNGF measure are compared to those from two dichotomized networks: a threshold and a multiscale backbone network. The results show that the WNGF generates valid results, consistent with those of the dichotomized network. In addition, it provides the following advantages: (i) it ensures information retention, (ii) since no alterations and decisions have to be made on how to dichotomize the network, the WNGF frees the user from the burden of making assumptions, (iii) it provides a nuanced understanding of each node's brokerage role. These advantages are of special importance when the role of less connected nodes is considered. The two empirical networks used here are for illustrative purposes. Possible applications of WNGF span beyond regional and organizational studies, and into all those contexts where retaining weights is important, for example by accounting for persisting or repeating edges compared to one-time interactions. WNGF can also be used to further analyze networks that measure how often people meet, talk, text, like, or retweet. WNGF makes a relevant methodological contribution as it offers a way to analyze brokerage in weighted, directed, and even complete graphs without information loss that can be used across disciplines and different type of networks.

cs.SI↗

arXiv2022

CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer

In this paper, we aim to devise a universally versatile style transfer method capable of performing artistic, photo-realistic, and video style transfer jointly, without seeing videos during training. Previous single-frame methods assume a strong constraint on the whole image to maintain temporal consistency, which could be violated in many cases. Instead, we make a mild and reasonable assumption that global inconsistency is dominated by local inconsistencies and devise a generic Contrastive Coherence Preserving Loss (CCPL) applied to local patches. CCPL can preserve the coherence of the content source during style transfer without degrading stylization. Moreover, it owns a neighbor-regulating mechanism, resulting in a vast reduction of local distortions and considerable visual quality improvement. Aside from its superior performance on versatile style transfer, it can be easily extended to other tasks, such as image-to-image translation. Besides, to better fuse content and style features, we propose Simple Covariance Transformation (SCT) to effectively align second-order statistics of the content feature with the style feature. Experiments demonstrate the effectiveness of the resulting model for versatile style transfer, when armed with CCPL.

cs.CV↗

arXiv2022

Observation of magnetism induced topological edge state in antiferromagnetic topological insulator MnBi4Te7

Breaking time reversal symmetry in a topological insulator may lead to quantum anomalous Hall effect and axion insulator phase. MnBi4Te7 is a recently discovered antiferromagnetic topological insulator with TN ~12.5 K, which is constituted of alternatively stacked magnetic layer (MnBi2Te4) and non-magnetic layer (Bi2Te3). By means of scanning tunneling spectroscopy, we clearly observe the electronic state present at a step edge of a magnetic MnBi2Te4 layer but absent at non-magnetic Bi2Te3 layers at 4.5 K. Furthermore, we find that as the temperature rises above TN, the edge state vanishes, while the point defect induced state persists upon temperature increasing. These results confirm the observation of magnetism induced edge states. Our analysis based on an axion insulator theory reveals that the nontrivial topological nature of the observed edge state.

cond-mat.mtrl-sci↗

arXiv2022

MobileFaceSwap: A Lightweight Framework for Video Face Swapping

Advanced face swapping methods have achieved appealing results. However, most of these methods have many parameters and computations, which makes it challenging to apply them in real-time applications or deploy them on edge devices like mobile phones. In this work, we propose a lightweight Identity-aware Dynamic Network (IDN) for subject-agnostic face swapping by dynamically adjusting the model parameters according to the identity information. In particular, we design an efficient Identity Injection Module (IIM) by introducing two dynamic neural network techniques, including the weights prediction and weights modulation. Once the IDN is updated, it can be applied to swap faces given any target image or video. The presented IDN contains only 0.50M parameters and needs 0.33G FLOPs per frame, making it capable for real-time video face swapping on mobile phones. In addition, we introduce a knowledge distillation-based method for stable training, and a loss reweighting module is employed to obtain better synthesized results. Finally, our method achieves comparable results with the teacher models and other state-of-the-art methods.

cs.CV↗