Searcharxiv⌕ Search

arXiv subjects

Feng Han

Publications and source records attributed to Feng Han.

At least 37 records · Page 2Linked to original sources

Kling-Omni Technical Report

We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supports a diverse range of user inputs, including text instructions, reference images, and video contexts, processing them into a unified multimodal representation to deliver cinematic-quality and highly-intelligent video content creation. To support these capabilities, we constructed a comprehensive data system that serves as the foundation for multimodal video creation. The framework is further empowered by efficient large-scale pre-training strategies and infrastructure optimizations for inference. Comprehensive evaluations reveal that Kling-Omni demonstrates exceptional capabilities in in-context generation, reasoning-based editing, and multimodal instruction following. Moving beyond a content creation tool, we believe Kling-Omni is a pivotal advancement toward multimodal world simulators capable of perceiving, reasoning, generating and interacting with the dynamic and complex worlds.

cs.CV↗

ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning

The field of controllable image generation has seen significant advancements, with various architectures improving generation layout consistency with control signals. However, contemporary methods still face challenges in bridging the semantic gap between input text prompts with sparse semantics and the target images, often over-relying on low-level control signals to infer regional details. To address this challenge, we propose ControlThinker, a novel framework that employs a "comprehend-then-generate" paradigm. Firstly, by incentivizing the visual reasoning capability of a MLLM, latent semantics from control images are mined to enrich text prompts. This enriched semantic understanding then seamlessly aids in image generation without the need for additional complex modifications. To further tackle the uncertainty arising from the ambiguity of control images, we encourage broader exploration of reasoning trajectories and select the optimal one using a metric-based output reward model (ORM). Extensive experimental results demonstrate that ControlThinker effectively mitigates the semantic gap between raw text prompts and target images, resulting in improved visual quality and semantic consistency across a wide range of benchmarks. The code and models are available at https://github.com/Maplebb/ControlThinker.

cs.CV↗

VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation

Recently, autoregressive image generation models have wowed audiences with their remarkable capability in creating surprisingly realistic images. Models such as GPT-4o and LlamaGen can not only produce images that faithfully mimic renowned artistic styles like Ghibli, Van Gogh, or Picasso, but also potentially generate Not-Safe-For-Work (NSFW) content, raising significant concerns regarding copyright infringement and ethical use. Despite these concerns, methods to safeguard autoregressive text-to-image models remain underexplored. Previous concept erasure methods, primarily designed for diffusion models that operate in denoising latent space, are not directly applicable to autoregressive models that generate images token by token. To address this critical gap, we propose Visual Contrast Exploitation (VCE), a novel framework comprising: (1) an innovative contrastive image pair construction paradigm that precisely decouples unsafe concepts from their associated content semantics, and (2) a sophisticated DPO-based training approach that enhances the model's ability to identify and leverage visual contrastive features from image pairs, enabling precise concept erasure. Our comprehensive experiments across three challenging tasks-artist style erasure, explicit content erasure, and object removal-demonstrate that our method effectively secures the model, achieving state-of-the-art results while erasing unsafe concepts and maintaining the integrity of unrelated safe concepts. The code and models are available at https://github.com/Maplebb/VCE.

cs.CV↗

Machine Learning-based Online Stability Lobe Diagram Estimation and Chatter Suppression Control in Milling Process

Chatter is a self-excited vibration in milling that degrades surface quality and accelerates tool wear. This paper presents an adaptive process controller that suppresses chatter by leveraging machine learning-based online estimation of the Stability Lobe Diagram (SLD) and surface roughness in the process. Stability analysis is conducted using the semi-discretization method for milling dynamics modeled by delay differential equations. An integrated machine learning framework estimates the SLD from sensor data and predicts surface roughness for chatter detection in real time. These estimates are integrated into an optimal controller that adaptively adjusts spindle speed to maintain process stability and improve surface finish. Simulations and experiments are performed to demonstrate the superior performance compared to the existing approaches.

eess.SY↗

Dual-LoRA and Quality-Enhanced Pseudo Replay for Multimodal Continual Food Learning

Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LMMs) in food analysis suffer from catastrophic forgetting when learning new tasks, requiring costly retraining from scratch. To address this, we propose a novel continual learning framework for multimodal food learning, integrating a Dual-LoRA architecture with Quality-Enhanced Pseudo Replay. We introduce two complementary low-rank adapters for each task: a specialized LoRA that learns task-specific knowledge with orthogonal constraints to previous tasks' subspaces, and a cooperative LoRA that consolidates shared knowledge across tasks via pseudo replay. To improve the reliability of replay data, our Quality-Enhanced Pseudo Replay strategy leverages self-consistency and semantic similarity to reduce hallucinations in generated samples. Experiments on the comprehensive Uni-Food dataset show superior performance in mitigating forgetting, representing the first effective continual learning approach for complex food tasks.

cs.LG↗

EmbeddingGemma: Powerful and Lightweight Text Representations

We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and geometric embedding distillation. We improve model robustness and expressiveness with a spread-out regularizer, and ensure generalizability by merging checkpoints from varied, optimized mixtures. Evaluated on the Massive Text Embedding Benchmark (MTEB) across multilingual, English, and code domains, EmbeddingGemma (300M) achieves state-of-the-art results. Notably, it outperforms prior top models, both proprietary and open, with fewer than 500M parameters, and provides performance comparable to models double its size, offering an exceptional performance-to-cost ratio. Remarkably, this lead persists when quantizing model weights or truncating embedding outputs. This makes EmbeddingGemma particularly well-suited for low-latency and high-throughput use cases such as on-device applications. We provide ablation studies exploring our key design choices. We release EmbeddingGemma to the community to promote further research.

cs.CL↗

MapComp: A Secure View-based Collaborative Analytics Framework for Join-Group-Aggregation

Join-group-aggregation (JGA) queries are fundamental to data analytics, yet executing them collaboratively across different parties poses significant privacy risks. Secure multi-party computation (MPC) offers a cryptographic solution. However, existing MPC-based JGA approaches consider only a one-time query paradigm and suffer from significant performance bottlenecks. It executes expensive join operations from scratch across multiple queries and employs inefficient group-aggregation (GA) protocols, both of which hinder their practical use for scalable, real-time analysis. This paper introduces MapComp, a novel view-based framework to facilitate JGA queries for secure collaborative analytics. Through specially crafted materialized views for join and novel design of GA protocols, MapComp removes duplicate join workload and expedites subsequent GA, improving the efficiency of JGA query execution. To address the challenge of continuous data updates, our materialized view offers payload-independence feature and provides significant efficiency improvements in view refreshing with free MPC overhead. This feature, on the other hand, also allows further acceleration for GA, where we devise multiple novel protocols that outperform prior works. Notably, our work represents the first endeavor to expedite secure collaborative JGA queries using materialized views. Our rigorous experiments demonstrate a significant advantage of MapComp, achieving up to a 308.9x improvement in efficiency over the baseline in real-world query simulations. Moreover, our optimized GA protocols achieve up to a 1140.5x improvement compared to prior oblivious sorting-based solutions.

cs.CR↗

Physics-informed Multiresolution Wavelet Neural Network Method for Solving Partial Differential Equations

In this paper, a physics-informed multiresolution wavelet neural network (PIMWNN) method is proposed for solving partial differential equations (PDEs). This method uses the multiresolution wavelet neural network (MWNN) to approximate unknown functions, then substituting the MWNN into PDEs and training the MWNN by least-squares algorithm. We apply the proposed method to various problems, including stationary/nonstationary advection, diffusion and advection-diffusion problems, and linear/nonlinear time-dependent problems. Numerical experiments show that the PIMWNN method can achieve higher accuracy and faster speed than Physics Informed Neural Networks (PINNs). Moreover, the PIMWNN method, being mesh-free, can handle different boundary conditions easily and solve the time-dependent problems efficiently. The proposed method is expected to solve the spectral bias problem in network training. These characteristics show the great potential of the PIMWNN method used in the field of numerical solving methods for PDEs.

math.NA↗

Gemini Embedding: Generalizable Embeddings from Gemini

In this report, we introduce Gemini Embedding, a state-of-the-art embedding model leveraging the power of Gemini, Google's most capable large language model. Capitalizing on Gemini's inherent multilingual and code understanding capabilities, Gemini Embedding produces highly generalizable embeddings for text spanning numerous languages and textual modalities. The representations generated by Gemini Embedding can be precomputed and applied to a variety of downstream tasks including classification, similarity, clustering, ranking, and retrieval. Evaluated on the Massive Multilingual Text Embedding Benchmark (MMTEB), which includes over one hundred tasks across 250+ languages, Gemini Embedding substantially outperforms prior state-of-the-art models, demonstrating considerable improvements in embedding quality. Achieving state-of-the-art performance across MMTEB's multilingual, English, and code benchmarks, our unified model demonstrates strong capabilities across a broad selection of tasks and surpasses specialized domain-specific models.

cs.CL↗

DuMo: Dual Encoder Modulation Network for Precise Concept Erasure

The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous methods safeguard the models by eliminating inappropriate concepts. Nonetheless, these models alter the parameters of the backbone network and exert considerable influences on the structural (low-frequency) components of the image, which undermines the model's ability to retain non-target concepts. In this work, we propose our Dual encoder Modulation network (DuMo), which achieves precise erasure of inappropriate target concepts with minimum impairment to non-target concepts. In contrast to previous methods, DuMo employs the Eraser with PRior Knowledge (EPR) module which modifies the skip connection features of the U-NET and primarily achieves concept erasure on details (high-frequency) components of the image. To minimize the damage to non-target concepts during erasure, the parameters of the backbone U-NET are frozen and the prior knowledge from the original skip connection features is introduced to the erasure process. Meanwhile, the phenomenon is observed that distinct erasing preferences for the image structure and details are demonstrated by the EPR at different timesteps and layers. Therefore, we adopt a novel Time-Layer MOdulation process (TLMO) that adjusts the erasure scale of EPR module's outputs across different layers and timesteps, automatically balancing the erasure effects and model's generative ability. Our method achieves state-of-the-art performance on Explicit Content Erasure, Cartoon Concept Removal and Artistic Style Erasure, clearly outperforming alternative methods. Code is available at https://github.com/Maplebb/DuMo

cs.CV↗

A technical solution for the rule of law, peace, security, and evolvability of global cyberspace -- solve the three genetic defects of IP network

Since its inception in the 1960s, the internet has profoundly transformed human life. However, its original design now struggles to meet the evolving demands of modern society. Three primary defects have emerged: First, the concentration of power among a few dominant entities has intensified international conflicts and widened the technological divide. Second, the Internet Protocol (IP)-based system lacks inherent security, leading to frequent global cybersecurity incidents. Third, the rigidity of the IP protocol has hindered the sustainable development of cyberspace, as it resists necessary adaptations and innovations. Addressing these issues is crucial for the future resilience and security of the global digital landscape. To address these challenges, we propose the Co-governed Multi-Identifier Network (CoG-MIN briefly as MIN), a novel network architecture that leverages blockchain technology to ensure equal participation of countries worldwide in cyberspace governance and the rule of law. As a next-generation network system, CoG-MIN integrates mechanisms such as user authentication, data signatures, and encryption to significantly enhance network security. In testing environments, CoG-MIN has consistently withstood extensive attacks during various international cybersecurity competitions. Additionally, CoG-MIN supports the evolution and interoperability of different identifier systems, remains IP-compatible, and facilitates a gradual transition away from IP, providing an adaptable ecosystem for diverse network architectures. This adaptability fosters the development and evolution of diverse network architectures within CoG-MIN, making it a natural progression for the internet's future development. We further introduce a trilogy of cyberspace security theorems... (Due to character limitations, the full abstract is available in the paper PDF.)

cs.CR↗

Explaining Model Overfitting in CNNs via GMM Clustering

Convolutional Neural Networks (CNNs) have demonstrated remarkable prowess in the field of computer vision. However, their opaque decision-making processes pose significant challenges for practical applications. In this study, we provide quantitative metrics for assessing CNN filters by clustering the feature maps corresponding to individual filters in the model via Gaussian Mixture Model (GMM). By analyzing the clustering results, we screen out some anomaly filters associated with outlier samples. We further analyze the relationship between the anomaly filters and model overfitting, proposing three hypotheses. This method is universally applicable across diverse CNN architectures without modifications, as evidenced by its successful application to models like AlexNet and LeNet-5. We present three meticulously designed experiments demonstrating our hypotheses from the perspectives of model behavior, dataset characteristics, and filter impacts. Through this work, we offer a novel perspective for evaluating the CNN performance and gain new insights into the operational behavior of model overfitting.

cs.LG↗

Hyperspectral Image Cross-Domain Object Detection Method based on Spectral-Spatial Feature Alignment

With consecutive bands in a wide range of wavelengths, hyperspectral images (HSI) have provided a unique tool for object detection task. However, existing HSI object detection methods have not been fully utilized in real applications, which is mainly resulted by the difference of spatial and spectral resolution between the unlabeled target domain and a labeled source domain, i.e. the domain shift of HSI. In this work, we aim to explore the unsupervised cross-domain object detection of HSI. Our key observation is that the local spatial-spectral characteristics remain invariant across different domains. For solving the problem of domain-shift, we propose a HSI cross-domain object detection method based on spectral-spatial feature alignment, which is the first attempt in the object detection community to the best of our knowledge. Firstly, we develop a spectral-spatial alignment module to extract domain-invariant local spatial-spectral features. Secondly, the spectral autocorrelation module has been designed to solve the domain shift in the spectral domain specifically, which can effectively align HSIs with different spectral resolutions. Besides, we have collected and annotated an HSI dataset for the cross-domain object detection. Our experimental results have proved the effectiveness of HSI cross-domain object detection, which has firstly demonstrated a significant and promising step towards HSI cross-domain object detection in the object detection community.

cs.CV↗

Video Summarization: Towards Entity-Aware Captions

Existing popular video captioning benchmarks and models deal with generic captions devoid of specific person, place or organization named entities. In contrast, news videos present a challenging setting where the caption requires such named entities for meaningful summarization. As such, we propose the task of summarizing news video directly to entity-aware captions. We also release a large-scale dataset, VIEWS (VIdeo NEWS), to support research on this task. Further, we propose a method that augments visual information from videos with context retrieved from external world knowledge to generate entity-aware captions. We demonstrate the effectiveness of our approach on three video captioning models. We also show that our approach generalizes to existing news image captions dataset. With all the extensive experiments and insights, we believe we establish a solid basis for future research on this challenging task.

cs.CV↗

PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs

Large Language Models (LLMs) have exhibited impressive capabilities in various tasks, yet their vast parameter sizes restrict their applicability in resource-constrained settings. Knowledge distillation (KD) offers a viable solution by transferring expertise from large teacher models to compact student models. However, traditional KD techniques face specific challenges when applied to LLMs, including restricted access to LLM outputs, significant teacher-student capacity gaps, and the inherited mis-calibration issue. In this work, we present PLaD, a novel preference-based LLM distillation framework. PLaD exploits the teacher-student capacity discrepancy to generate pseudo-preference pairs where teacher outputs are preferred over student outputs. Then, PLaD leverages a ranking loss to re-calibrate student's estimation of sequence likelihood, which steers the student's focus towards understanding the relative quality of outputs instead of simply imitating the teacher. PLaD bypasses the need for access to teacher LLM's internal states, tackles the student's expressivity limitations, and mitigates the student mis-calibration issue. Through extensive experiments on two sequence generation tasks and with various LLMs, we demonstrate the effectiveness of our proposed PLaD framework.

cs.CL↗

Multi-Scale Dilated Convolution Network for Long-Term Time Series Forecasting

Accurate forecasting of long-term time series has important applications for decision making and planning. However, it remains challenging to capture the long-term dependencies in time series data. To better extract long-term dependencies, We propose Multi Scale Dilated Convolution Network (MSDCN), a method that utilizes a shallow dilated convolution architecture to capture the period and trend characteristics of long time series. We design different convolution blocks with exponentially growing dilations and varying kernel sizes to sample time series data at different scales. Furthermore, we utilize traditional autoregressive model to capture the linear relationships within the data. To validate the effectiveness of the proposed approach, we conduct experiments on eight challenging long-term time series forecasting benchmark datasets. The experimental results show that our approach outperforms the prior state-of-the-art approaches and shows significant inference speed improvements compared to several strong baseline methods.

cs.LG↗

Gaussian Process-Based Learning Control of Underactuated Balance Robots with an External and Internal Convertible Modeling Structure

External and internal convertible (EIC) form-based motion control is one of the effective designs of simultaneously trajectory tracking and balance for underactuated balance robots. Under certain conditions, the EIC-based control design however leads to uncontrolled robot motion. We present a Gaussian process (GP)-based data-driven learning control for underactuated balance robots with the EIC modeling structure. Two GP-based learning controllers are presented by using the EIC structure property. The partial EIC (PEIC)-based control design partitions the robotic dynamics into a fully actuated subsystem and one reduced-order underactuated system. The null-space EIC (NEIC)-based control compensates for the uncontrolled motion in a subspace, while the other closed-loop dynamics are not affected. Under the PEIC- and NEIC-based, the tracking and balance tasks are guaranteed and convergence rate and bounded errors are achieved without causing any uncontrolled motion by the original EIC-based control. We validate the results and demonstrate the GP-based learning control design performance using two inverted pendulum platforms.

cs.RO↗

NeRFTAP: Enhancing Transferability of Adversarial Patches on Face Recognition using Neural Radiance Fields

Face recognition (FR) technology plays a crucial role in various applications, but its vulnerability to adversarial attacks poses significant security concerns. Existing research primarily focuses on transferability to different FR models, overlooking the direct transferability to victim's face images, which is a practical threat in real-world scenarios. In this study, we propose a novel adversarial attack method that considers both the transferability to the FR model and the victim's face image, called NeRFTAP. Leveraging NeRF-based 3D-GAN, we generate new view face images for the source and target subjects to enhance transferability of adversarial patches. We introduce a style consistency loss to ensure the visual similarity between the adversarial UV map and the target UV map under a 0-1 mask, enhancing the effectiveness and naturalness of the generated adversarial face images. Extensive experiments and evaluations on various FR models demonstrate the superiority of our approach over existing attack techniques. Our work provides valuable insights for enhancing the robustness of FR systems in practical adversarial settings.

cs.CV↗