Yueqian Lin

Preprint · 2025 Generative Artificial Intelligence (GenAI) applies models and algorithms such as Large Language Model (LLM) and Foundation Model (FM) to generate new data. GenAI, as a promising approach, enables advanced capabilities in various applications, including tex ... Full text Cite

SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval

Preprint · December 16, 2024 Link to item Cite

Yueqian Lin

Scholarly Works - Preprints

FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching

Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding

MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

Bridging the Perception Gap: A Lightweight Coarse-to-Fine Architecture for Edge Audio Systems

AsyncVoice Agent: Real-Time Explanation for LLM Planning and Reasoning

Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap

HippoMM: Hippocampal-inspired Multimodal Memory for Long Audiovisual Event Understanding

GenAI at the Edge: Comprehensive Survey on Empowering Edge Devices

SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval

Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey

SD-NAE: Generating Natural Adversarial Examples with Stable Diffusion

BiSinger: Bilingual Singing Voice Synthesis

RTVis: Research Trend Visualization Toolkit