Picture for Fanghua Ye

Fanghua Ye

UNComp: Uncertainty-Aware Long-Context Compressor for Efficient Large Language Model Inference

Add code
Oct 04, 2024
Viaarxiv icon

UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation

Add code
Oct 03, 2024
Viaarxiv icon

Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism

Add code
Jul 24, 2024
Viaarxiv icon

Synergizing Foundation Models and Federated Learning: A Survey

Add code
Jun 18, 2024
Viaarxiv icon

Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality

Add code
May 16, 2024
Viaarxiv icon

Anchor-based Large Language Models

Add code
Feb 16, 2024
Viaarxiv icon

Benchmarking LLMs via Uncertainty Quantification

Add code
Jan 23, 2024
Viaarxiv icon

Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models

Add code
Jan 17, 2024
Viaarxiv icon

Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking

Add code
Dec 14, 2023
Viaarxiv icon

Turn-Level Active Learning for Dialogue State Tracking

Add code
Oct 23, 2023
Viaarxiv icon