Search Results for author:
Found 19 papers, 9 papers with code
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora
We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol
Building on this taxonomy, we develop benchmark and training data that support the evaluation and improvement of LLMs' capabilities in identifying safety risks within MCP interactions.
Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
For OpenThinker-7B, a strong reasoning model that significantly outperforms its base model Qwen2. 5-7B-Instruct across diverse subjects, our method enhances its general reasoning capabilities, with +2. 05% and +8. 98% accuracy improvement on the MMLU and LegalBench benchmark, respectively.
A Deep Single Image Rectification Approach for Pan-Tilt-Zoom Cameras
This paper presents a Forward Distortion and Backward Warping Network (FDBW-Net), a novel framework for wide-angle image rectification.
PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance
We evaluate the latest LLMs, including the recent reasoner models QwQ-32B and Deepseek R1.
Top Ten Challenges Towards Agentic Neural Graph Databases
This paper introduces Agentic Neural Graph Databases (Agentic NGDBs), which extend NGDBs with three core functionalities: autonomous query construction, neural query execution, and continuous learning.
Node Level Graph Autoencoder: Unified Pretraining for Textual Graph Learning
Textual graph representation learning aims to generate low-dimensional feature embeddings from textual graphs that can improve the performance of downstream tasks.
Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
We initially propose Overwrite Supervised Fine-tuning (OSFT) for effective backdoor removal when the trigger is known.
CFMW: Cross-modality Fusion Mamba for Multispectral Object Detection under Adverse Weather Conditions
Furthermore, we introduce the Cross-modality Fusion Mamba with Weather-removal (CFMW) to augment detection accuracy in adverse weather conditions.
Federated Neural Graph Databases
However, existing NGDBs are typically designed to operate on a single graph, limiting their ability to reason across multiple graphs.
Privacy-Preserved Neural Graph Databases
Neural graph databases (NGDBs) have emerged as a powerful paradigm that combines the strengths of graph databases (GDBs) and neural networks to enable efficient storage, retrieval, and analysis of graph-structured data which can be adaptively trained with LLMs.
User Consented Federated Recommender System Against Personalized Attribute Inference Attack
However, the recommendation model learned by a common FedRec may still be vulnerable to private information leakage risks, particularly attribute inference attacks, which means that the attacker can easily infer users' personal attributes from the learned model.
PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models
Lastly, PrivLM-Bench performs existing privacy attacks on LMs with pre-defined privacy objectives as the empirical evaluation results.
Privacy in Large Language Models: Attacks, Defenses and Future Directions
The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines.
Independent Distribution Regularization for Private Graph Embedding
Additionally, we introduce a novel regularization to enforce the independence of the encoders.
Universal adaptive optics for microscopy through embedded neural network control
Unlike previous ML methods, we used a bespoke neural network (NN) architecture, designed using physical understanding of image formation, that was embedded in the control loop of the microscope.
SOUP: Spatial-Temporal Demand Forecasting and Competitive Supply
In this setting, an assignment authority is to assign agents to requests such that the average idle time of the agents is minimized.
Databases Signal Processing
Practical sensorless aberration estimation for 3D microscopy with deep learning
Additionally, we study the predictability of individual aberrations with respect to their data requirements and find that the symmetry of the wavefront plays a crucial role.
An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking
We highlight a practical yet rarely discussed problem in dialogue state tracking (DST), namely handling unknown slot values.
