Search Results for author:
Found 83 papers, 43 papers with code
CronusVLA: Transferring Latent Motion Across Time for Multi-Frame Prediction in Manipulation
We propose CronusVLA, a unified framework that extends single-frame VLA models to the multi-frame paradigm through an efficient post-training stage.
Video World Models with Long-term Spatial Memory
Emerging world models autoregressively generate video frames in response to actions, such as camera movements and text prompts, among other control signals.
Training-Free Watermarking for Autoregressive Image Generation
However, existing generative watermarking methods are mainly designed for diffusion models while watermarking for autoregressive image generation models remains largely underexplored.
Lessons from Deploying Learning-based CSI Localization on a Large-Scale ISAC Platform
In recent years, Channel State Information (CSI), recognized for its fine-grained spatial characteristics, has attracted increasing attention in WiFi-based indoor localization.
WORLDMEM: Long-term Consistent World Simulation with Memory
World simulation has gained increasing popularity due to its ability to model virtual environments and predict the consequences of actions.
Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation
In this work, we present the systematic review of VLM-based detection and segmentation, view VLM as the foundational model and conduct comprehensive evaluations across multiple downstream tasks for the first time: 1) The evaluation spans eight detection scenarios (closed-set detection, domain adaptation, crowded objects, etc.)
HeteRAG: A Heterogeneous Retrieval-augmented Generation Framework with Decoupled Knowledge Representations
The retrieval step benefits from comprehensive information to improve retrieval accuracy, whereas excessively long chunks may introduce redundant contextual information, thereby diminishing both the effectiveness and efficiency of the generation process.
OmniCam: Unified Multimodal Video Generation via Camera Control
Camera control, which achieves diverse visual effects by changing camera position and pose, has attracted widespread attention.
A Survey on Remote Sensing Foundation Models: From Vision to Multimodality
This paper provides a comprehensive review of the state-of-the-art in vision and multimodal foundation models for remote sensing, focusing on their architecture, training methods, datasets and application scenarios.
Language-based Image Colorization: A Benchmark and Beyond
In view of the lack of a comprehensive review of language-based colorization literature, we conduct a thorough analysis and benchmarking.
Alias-Free Latent Diffusion Models:Improving Fractional Shift Equivariance of Diffusion Latent Space
Latent Diffusion Models (LDMs) are known to have an unstable generation process, where even small perturbations or shifts in the input noise can lead to significantly different outputs.
MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
In this paper, we explore human multiview diffusion models at the megapixel level and introduce a solution called mesh attention to enable training at 1024x1024 resolution.
Balanced Image Stylization with Style Matching Score
We present Style Matching Score (SMS), a novel optimization method for image stylization with diffusion models.
PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion Model
At the heart of our method is a plug-and-play phase transfer mechanism that dynamically and progressively transplants diffusion features' phase spectrum from the denoising process to reconstruct the reference image into the one to sample the generated illusion image, realizing deep fusion of the reference structural information and the textual semantic information in the diffusion model latent space.
OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images
However, existing OVD methods for remote sensing (RS) images are constrained by small-scale datasets and fail to address the unique challenges of remote sensing interpretation, include oriented object detection and the need for both high precision and real-time performance in diverse scenarios.
Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support
Large language models (LLMs), particularly those with reasoning capabilities, have rapidly advanced in recent years, demonstrating significant potential across a wide range of applications.
Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
Latent Diffusion Models (LDMs) are known to have an unstable generation process, where even small perturbations or shifts in the input noise can lead to significantly different outputs.
Imagine360: Immersive 360 Video Generation from Perspective Anchor
$360^\circ$ videos offer a hyper-immersive experience that allows the viewers to explore a dynamic scene from full 360 degrees.
Trajectory Attention for Fine-grained Video Motion Control
This paper introduces trajectory attention, a novel approach that performs attention along available pixel trajectories for fine-grained camera motion control.
GaussianAnything: Interactive Point Cloud Flow Matching For 3D Object Generation
While 3D content generation has advanced significantly, existing methods still face challenges with input formats, latent space design, and output representations.
Unified Generative and Discriminative Training for Multi-modal Large Language Models
Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval, yet struggles with complex scenarios requiring fine-grained semantic differentiation.
GroupDiff: Diffusion-based Group Portrait Editing
The training data engine covers the diverse needs of group portrait editing.
LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation
A desired virtual 3D scene should 1) exhibit omnidirectional view consistency, and 2) allow for free exploration in complex scene hierarchies.
Deep Uncertainty-Based Explore for Index Construction and Retrieval in Recommendation System
In recommendation systems, the relevance and novelty of the final results are selected through a cascade system of Matching -> Ranking -> Strategy.
Intelligent Artistic Typography: A Comprehensive Review of Artistic Text Design and Generation
Artistic text generation includes artistic text stylization and semantic typography.
SEED-Story: Multimodal Long Story Generation with Large Language Model
We further propose multimodal attention sink mechanism to enable the generation of stories with up to 25 sequences (only 10 for training) in a highly efficient autoregressive manner.
MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations
With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes rapid progress.
Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond
Following the taxonomy of context-based, generative learning, and contrastive learning approaches, we make a thorough review and benchmark of existing works and shed light on the future possible directions.
Video Diffusion Models are Training-free Motion Interpreter and Controller
MOFT provides a distinct set of benefits, including the ability to encode comprehensive motion information with clear interpretability, extraction without the need for training, and generalizability across diverse architectures.
Grounded 3D-LLM with Referent Tokens
To facilitate the use of referent tokens in subsequent language modeling, we provide a large-scale, automatically curated grounded scene-text dataset with over 1 million phrase-to-region correspondences and introduce Contrastive Language-Scene Pre-training (CLASP) to perform phrase-level scene-text alignment using this data.
FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation
In this paper, we introduce FRESCO, intra-frame correspondence alongside inter-frame correspondence to establish a more robust spatial-temporal constraint.
LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation
The latent is decoded by a transformer-based decoder into a high-capacity 3D neural field.
Forward Learning of Graph Neural Networks
To address these limitations, the forward-forward algorithm (FF) was recently proposed as an alternative to BP in the image classification domain, which trains NNs by performing two forward passes over positive and negative data.
Causal Multi-Label Feature Selection in Federated Setting
Multi-label feature selection serves as an effective mean for dealing with high-dimensional multi-label data.
3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
Specifically, it is powered by a text-conditioned tri-plane latent diffusion model, which quickly generates coarse 3D samples for fast prototyping.
PRIME: Protect Your Videos From Malicious Editing
With the development of generative models, the quality of generated content keeps increasing.
A New Creative Generation Pipeline for Click-Through Rate with Stable Diffusion Model
2) Prompt model is designed to generate individualized creatives for different user groups, which can further improve the diversity and quality.
Deep Ensemble Shape Calibration: Multi-Field Post-hoc Calibration in Online Advertising
These methods typically involve the training of calibrators using a validation set and subsequently applying these calibrators to correct the original estimated values during online inference.
Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems
Huge embedding tables in modern deep learning recommender models (DLRM) require prohibitively large memory during training and inference.
Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs
We empirically show that sparse attention not only reduces computational demands but also enhances model performance in both NLP and multi-modal tasks.
HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image
Extensive experiments demonstrate the effectiveness of HyperDreamer in modeling region-aware materials with high-resolution textures and enabling user-friendly editing.
VideoBooth: Diffusion-based Video Generation with Image Prompts
In this paper, we study the task of video generation with image prompts, which provide more accurate and direct content control beyond the text prompts.
Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics
Defect inspection is paramount within the closed-loop manufacturing system.
Denoising Diffusion Step-aware Models
Denoising Diffusion Probabilistic Models (DDPMs) have garnered popularity for data generation across various domains.
DeformToon3D: Deformable 3D Toonification from Neural Radiance Fields
In this paper, we address the challenging problem of 3D toonification, which involves transferring the style of an artistic domain onto a target 3D face with stylized geometry and texture.
Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translation
The challenges of this task lie in the complexity of the scenes, the unique features of anime style, and the lack of high-quality datasets to bridge the domain gap.
Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
The framework includes two parts: key frame translation and full video translation.
GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation
In this paper, we introduce a novel versatile framework, Generative Prior-guided UNsupervised Image-to-image Translation (GP-UNIT), that improves the quality, applicability and controllability of the existing translation models.
Graph Exploration Matters: Improving both individual-level and system-level diversity in WeChat Feed Recommender
Graph-based retrieval strategies are inevitably hijacked by heavy users and popular items, leading to the convergence of candidates for users and the lack of system-level diversity.
Text2Performer: Text-Driven Human Video Generation
In this work, we present Text2Performer to generate vivid human videos with articulated motions from texts.
StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces
Recent advances in face manipulation using StyleGAN have produced impressive results.
Learning to Rank Normalized Entropy Curves with Differentiable Window Transformation
We also introduce a novel differentiable indexing method for the proposed adaptive curve transformation, which allows gradients with respect to the discrete indices to flow freely through the curve transformation layer, enabling the learned window sizes to be updated flexibly during training.
MGTAB: A Multi-Relational Graph-Based Twitter Account Detection Benchmark
However, in addition to low annotation quality, existing benchmarks generally have incomplete user relationships, suppressing graph-based account detection research.
Ranked #1 on
Stance Detection
on MGTAB
DeformToon3D: Deformable Neural Radiance Fields for 3D Toonification
In this paper, we address the challenging problem of 3D toonification, which involves transferring the style of an artistic domain onto a target 3D face with stylized geometry and texture.
Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion
In this paper, we study the challenging problem of 3D GAN inversion where a latent code is predicted given a single face image to faithfully recover its 3D shapes and detailed textures.
VToonify: Controllable High-Resolution Portrait Video Style Transfer
Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these image-oriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing non-facial details and temporal inconsistency.
Text2Human: Text-Driven Controllable Human Image Generation
In this work, we present a text-driven controllable framework, Text2Human, for a high-quality and diverse human generation.
Select and Calibrate the Low-confidence: Dual-Channel Consistency based Graph Convolutional Networks
The Graph Convolutional Networks (GCNs) have achieved excellent results in node classification tasks, but the model's performance at low label rates is still unsatisfactory.
Unsupervised Image-to-Image Translation with Generative Prior
In this work, we present a novel framework, Generative Prior-guided UNsupervised Image-to-image Translation (GP-UNIT), to improve the overall quality and applicability of the translation algorithm.
Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer
Recent studies on StyleGAN show high performance on artistic portrait generation by transfer learning with limited data.
ShapeEditer: a StyleGAN Encoder for Face Swapping
In this paper, we propose a novel encoder, called ShapeEditor, for high-resolution, realistic and high-fidelity face exchange.
Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
Traditional methods such as resampling, reweighting, and synthetic samples that deal with imbalanced datasets are no longer applicable in GNN.
Towards Efficient Local Causal Structure Learning
Local causal structure learning aims to discover and distinguish direct causes (parents) and direct effects (children) of a variable of interest from data.
Learning causal representations for robust domain adaptation
In this paper, we study the cases where at the training phase the target domain data is unavailable and only well-labeled source domain data is available, called robust domain adaptation.
Consistent Video Style Transfer via Relaxation and Regularization
In this article, we address the problem by jointly considering the intrinsic properties of stylization and temporal consistency.
BARS-CTR: Open Benchmarking for Click-Through Rate Prediction
We have publicly released the benchmarking code, evaluation protocols, and hyper-parameter settings of our work to promote reproducible research in this field.
New opportunities at the photon energy frontier
Ultra-peripheral collisions (UPCs) involving heavy ions and protons are the energy frontier for photon-mediated interactions.
High Energy Physics - Phenomenology High Energy Physics - Experiment Nuclear Experiment
From Design Draft to Real Attire: Unaligned Fashion Image Translation
Moreover, built upon the sampling network, we present design draft to real fashion item translation network (D2RNet), where two separate translation streams that focus on texture and shape, respectively, are combined tactfully to get both benefits.
Towards Coding for Human and Machine Vision: A Scalable Image Coding Approach
In this paper, we come up with a novel image coding framework by leveraging both the compressive and the generative models, to support machine vision and human perception tasks jointly.
Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches
We present a sketch refinement strategy, as inspired by the coarse-to-fine drawing process of the artists, which we show can help our model well adapt to casual and varied sketches without the need for real sketch training data.
Residual Encoder-Decoder Network for Deep Subspace Clustering
Subspace clustering aims to cluster unlabeled data that lies in a union of low-dimensional linear subspaces.
Towards Efficient Local Causal Structure Learning
To tackle this issue, we propose a novel Efficient Local Causal Structure learning algorithm, named ELCS.
Semi-supervised representation learning via dual autoencoders for domain adaptation
Domain adaptation aims to exploit the knowledge in source domain to promote the learning tasks in target domain, which plays a critical role in real-world applications.
TE141K: Artistic Text Benchmark for Text Effect Transfer
To the best of our knowledge, this is the largest dataset for text effect transfer to date.
Controllable Artistic Text Style Transfer via Shape-Matching GAN
In this paper, we present the first text style transfer network that allows for real-time control of the crucial stylistic degree of the glyph through an adjustable parameter.
Three-Stage Subspace Clustering Framework with Graph-Based Transformation and Optimization
The affinity matrix is obtained in the first stage, then it goes through the second stage, where the proposed GBTO is applied to generate a reconstructed affinity matrix with more authentic similarity between data points.
Restricted Connection Orthogonal Matching Pursuit For Sparse Subspace Clustering
In this paper, we propose a noise-robust algorithm, Restricted Connection Orthogonal Matching Pursuit for Sparse Subspace Clustering (RCOMP-SSC), to improve the clustering accuracy and maintain the low computational time by restricting the number of connections of each data point during the iteration of OMP.
TET-GAN: Text Effects Transfer via Stylization and Destylization
The key idea is to train our network to accomplish both the objective of style transfer and style removal, so that it can learn to disentangle and recombine the content and style features of text effects images.
Context-Aware Text-Based Binary Image Stylization and Synthesis
The stylization is then followed by a context-aware layout design algorithm, where cues for both seamlessness and aesthetics are employed to determine the optimal layout of the shape in the background.
Erase or Fill? Deep Joint Recurrent Rain Removal and Reconstruction in Videos
In this paper, we address the problem of video rain removal by constructing deep recurrent convolutional networks.
Awesome Typography: Statistics-Based Text Effects Transfer
It allows our algorithm to produce artistic typography that fits for both local texture patterns and the global spatial distribution in the example.
