1

Federated Domain Generalization with Domain-specific Soft Prompts Generation
Prompt learning has become an efficient paradigm for adapting CLIP to downstream tasks. Compared with traditional fine-tuning, prompt …
Cite arXiv theCVF
Publicly Verifiable Private Information Retrieval Protocols Based on Function Secret Sharing
Private Information Retrieval (PIR) is a fundamental cryptographic primitive that enables users to retrieve data from a database …
Cite arXiv Springer
Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning
Previous continual learning setups for embodied intelligence focused on executing low-level actions based on human commands, neglecting …
Cite arXiv ACL
Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning
MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts
One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption …
Cite arXiv ACL
MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts
RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models
Object Navigation (ObjectNav) is a fundamental task in embodied artificial intelligence. Although significant progress has been made in …
Cite arXiv ACL
RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models
BAGNet: A Boundary-Aware Graph Attention Network for 3D Point Cloud Semantic Segmentation
Since the point cloud data is inherently irregular and unstructured, point cloud semantic segmentation has always been a challenging …
Cite arXiv IEEE
BAGNet: A Boundary-Aware Graph Attention Network for 3D Point Cloud Semantic Segmentation
Bridging the Modality Gap: Semantic-Calibrated Zero-shot Speech Emotion Captioning
Speech Emotion Captioning (SEC) has emerged as an increasingly prominent research area. The emotional content expressed through human …
Cite IEEE
Bridging the Modality Gap: Semantic-Calibrated Zero-shot Speech Emotion Captioning
Data-free Black-box Knowledge Amalgamation
A massive number of well-trained models with promising performances have been released nowadays; exploring reusing them would benefit …
Cite IEEE
Data-free Black-box Knowledge Amalgamation
Generalized Audio Deepfake Detection Using Frame-level Latent Information Entropy
Generalizability, the capacity of a robust model to perform effectively on unseen data, is crucial for audio deepfake detection due to …
Cite arXiv IEEE
Generalized Audio Deepfake Detection Using Frame-level Latent Information Entropy
Logic Consistency Makes Large Language Models Personalized Reasoning Teachers
Large Language Models (LLMs) have advanced natural language processing, particularly through Chain-of-Thought (CoT) reasoning, but …
Cite IEEE
Logic Consistency Makes Large Language Models Personalized Reasoning Teachers