Search Results for author:
Found 42 papers, 26 papers with code
Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity
With the growing use of large language models (LLMs) hosted on cloud platforms to offer inference services, privacy concerns about the potential leakage of sensitive information are escalating.
VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization
Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils subtle threats beyond the reach of conventional safeguards.
Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction
Our work sheds light on the study of NLI and will bring research interest on cross-document cross-lingual context understanding, hallucination elimination and interpretability inference.
AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
Introducing AgiBot World, a large-scale platform comprising over 1 million trajectories across 217 tasks in five deployment scenarios, we achieve an order-of-magnitude increase in data scale compared to existing datasets.
FedMABench: Benchmarking Mobile Agents on Decentralized Heterogeneous User Data
FedMABench features 6 datasets with 30+ subsets, 8 federated algorithms, 10+ base models, and over 800 apps across 5 categories, providing a comprehensive framework for evaluating mobile agents across diverse environments.
VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation
The VideoUFO comprises over 1. 09 million video clips, each paired with both a brief and a detailed caption (description).
GSCE: A Prompt Framework with Enhanced Reasoning for Reliable LLM-driven Drone Control
The integration of Large Language Models (LLMs) into robotic control, including drones, has the potential to revolutionize autonomous systems.
A Unified Modeling Framework for Automated Penetration Testing
The integration of artificial intelligence into automated penetration testing (AutoPT) has highlighted the necessity of simulation modeling for the training of intelligent agents, due to its cost-efficiency and swift feedback capabilities.
Captured by Captions: On Memorization and its Mitigation in CLIP Models
Multi-modal models, such as CLIP, have demonstrated strong performance in aligning visual and textual representations, excelling in tasks like image retrieval and zero-shot classification.
MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users
Given the vast population of global mobile phone users, if automated data collection from them becomes feasible, the resulting data volume and the subsequently trained mobile agents could reach unprecedented levels.
Origin Identification for Text-Guided Image-to-Image Diffusion Models
Subsequently, it is demonstrated that such a simple linear transformation can be generalized across different diffusion models.
A Variance Minimization Approach to Temporal-Difference Learning
Fast-converging algorithms are a contemporary requirement in reinforcement learning.
TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation
In this paper, we introduce TIP-I2V, the first large-scale dataset of over 1. 70 million unique user-provided Text and Image Prompts specifically for Image-to-Video generation.
Generalizable Humanoid Manipulation with 3D Diffusion Policies
However, autonomous manipulation by humanoid robots has largely been restricted to one specific scene, primarily due to the difficulty of acquiring generalizable skills and the expensiveness of in-the-wild humanoid robot data.
KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server
The success of large language models (LLMs) facilitate many parties to fine-tune LLMs on their own private data.
Image Copy Detection for Diffusion Models
Existing Image Copy Detection (ICD) models, though accurate in detecting hand-crafted replicas, overlook the challenge from diffusion models.
Localizing Memorization in SSL Vision Encoders
Recent work on studying memorization in self-supervised learning (SSL) suggests that even though SSL encoders are trained on millions of images, they still memorize individual data points.
MonoFormer: One Transformer for Both Diffusion and Autoregression
Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for both text and visual generation.
Replication in Visual Diffusion Models: A Survey and Outlook
In this survey, we provide the first comprehensive review of replication in visual diffusion models, marking a novel contribution to the field by systematically categorizing the existing studies into unveiling, understanding, and mitigating this phenomenon.
AnyPattern: Towards In-context Image Copy Detection
To accommodate the "seen $\rightarrow$ unseen" generalization scenario, we construct the first large-scale pattern dataset named AnyPattern, which has the largest number of tamper patterns ($90$ for training and $10$ for testing) among all the existing ones.
TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision
Among these works, many of them utilize in-context examples to achieve generalization without the need for fine-tuning, while few of them have considered the problem of how to select and effectively utilize these examples.
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
However, Sora, along with other text-to-video diffusion models, is highly reliant on prompts, and there is no publicly available dataset that features a study of text-to-video prompts.
OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning
Trained on massive publicly available data, large language models (LLMs) have demonstrated tremendous success across various fields.
FedRSU: Federated Learning for Scene Flow Estimation on Roadside Units
In this paper, we introduce FedRSU, an innovative federated learning framework for self-supervised scene flow estimation.
Memorization in Self-Supervised Learning Improves Downstream Generalization
Our definition compares the difference in alignment of representations for data points and their augmented views returned by both encoders that were trained on these data points and encoders that were not.
Two-Factor Authentication Approach Based on Behavior Patterns for Defeating Puppet Attacks
Furthermore, we conducted comparative experiments to validate the superiority of combining image features and timing characteristics within PUPGUARD for enhancing resistance against puppet attacks.
Feature-compatible Progressive Learning for Video Copy Detection
Video Copy Detection (VCD) has been developed to identify instances of unauthorized or duplicated video content.
TransHP: Image Classification with Hierarchical Prompting
This paper explores a hierarchical prompting mechanism for the hierarchical image classification (HIC) task.
V$^2$L: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval
While model ensemble is common, we show that combining the vision models and vision-language models brings particular benefits from their complementarity and is a key factor to our superiority.
A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detection
Moreover, this paper further reveals a unique difficulty for solving the hard negative problem in ICD, i. e., there is a fundamental conflict between current metric learning and ICD.
Results and findings of the 2021 Image Similarity Challenge
The 2021 Image Similarity Challenge introduced a dataset to serve as a new benchmark to evaluate recent image copy detection methods.
Bag of Tricks and A Strong baseline for Image Copy Detection
In this paper, a bag of tricks and a strong baseline are proposed for image copy detection.
D$^2$LV: A Data-Driven and Local-Verification Approach for Image Copy Detection
In this paper, a data-driven and local-verification (D$^2$LV) approach is proposed to compete for Image Similarity Challenge: Matching Track at NeurIPS'21.
Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction
While single-view 3D reconstruction has made significant progress benefiting from deep shape representations in recent years, garment reconstruction is still not solved well due to open surfaces, diverse topologies and complex geometric details.
DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations
In this way, human annotations are no longer required, and it is scalable to large and diverse real-world datasets.
Generalizable Person Re-identification
Unsupervised Domain Adaptation
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
Scenario Forecast of Cross-border Electric Interconnection towards Renewables in South America
Cross-border Electric Interconnection towards renewables is a promising solution for electric sector under the UN 2030 sustainable development goals which is widely promoted in emerging economies.
Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond
This paper proposes a novel light-weight module, the Attentive WaveBlock (AWB), which can be integrated into the dual networks of mutual learning to enhance the complementarity and further depress noise in the pseudo-labels.
Ranked #3 on
Unsupervised Domain Adaptation
on Duke to MSMT
A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework
Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices.
Adapted Center and Scale Prediction: More Stable and More Accurate
Therefore, in order to enjoy the simplicity of anchor-free detectors and the accuracy of two-stage ones simultaneously, we propose some adaptations based on a detector, Center and Scale Prediction(CSP).
Ranked #1 on
Pedestrian Detection
on CityPersons
(Bare MR^-2 metric, using extra
training data)
