YL
Yueqian Lin
cs.AIcs.LGeess.AScs.CVcs.SDcs.CLcs.MMcs.ROcs.HCcs.MA
On Valency
published · living versionsW_jm3vhkc9·v1 · currentpublished
Will My Assistant Remember My Allergy? What Personal LLM Assistants Forget When Conversation Memory Is Compressed
with Lichen Zhu, Yiheng Wang, Yudong Liu, Hai "Helen" Li +1
1 version
Preprints & journals
27 papers in the corpus · 2022–2026Gamma: Grounded Multi-Agent Memory with Mechanical Audit for Memory-Intensive Manipulation2610.12793v1 · Yudong Liu, Yueqian Lin, Zijia Tang et al.2026 · 0 citationsarXiv
Stable Scores, Unstable Answers: Frame Phase and Option Order in Video Multiple-Choice Evaluation2610.08649v1 · Lichen Zhu, Yiheng Wang, Yueqian Lin et al.2026 · 0 citationsarXiv
Knowing When to Trust a Prior: Reliability-Gated Cue Fusion for Video Gaze Prediction2610.08663v1 · Lichen Zhu, Yueqian Lin, Yiheng Wang et al.2026 · 0 citationsarXiv
Coupled but Late: Turn-Taking Between Full-Duplex Speech Models in Unscripted Dialogue2610.08683v1 · Lichen Zhu, Yueqian Lin, Yiheng Wang et al.2026 · 0 citationsarXiv
Will My Assistant Remember My Allergy? What Personal LLM Assistants Forget When Conversation Memory Is Compressed2609.05767v1 · Lichen Zhu, Yueqian Lin, Yiheng Wang et al.2026 · 0 citationsarXivon Valency
Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference2605.02739v1 · Yudong Liu, Yuan Li, Zijia Tang et al.2026 · 0 citationsarXiv
FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching2604.17720v1 · Yuzhe Fu, Hancheng Ye, Cong Guo et al.2026 · 0 citationsarXiv
T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning2603.03790v1 · Qinsi Wang, Hancheng Ye, Jinhee Kim et al.2026 · 0 citationsarXiv
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models2603.02482v2 · Zhongxi Wang, Yueqian Lin, Jingyang Zhang et al.2026 · 0 citationsarXiv
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks2602.12670v4 · Xiangyi Li, Yimin Liu, Wenbo Chen et al.2026 · 2 citationsarXiv
Bridging the Perception Gap: A Lightweight Coarse-to-Fine Architecture for Edge Audio Systems2601.15676v1 · Hengfan Zhang, Yueqian Lin, Hai Helen Li et al.2026 · 0 citationsarXiv
LLaViDA: A Large Language Vision Driving Assistant for Explicit Reasoning and Enhanced Trajectory Planning2512.18211v1 · Yudong Liu, Spencer Hallyburton, Jiwoo Kim et al.2025 · 0 citationsarXiv
AsyncVoice Agent: Real-Time Explanation for LLM Planning and Reasoning2510.16156v1 · Yueqian Lin, Zhengmian Hu, Jayakumar Subramanian et al.2025 · 0 citationsarXiv
KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems2510.12872v2 · Hancheng Ye, Zhengqi Gao, Mingyuan Ma et al.2025 · 4 citationsarXiv
Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap2509.26542v1 · Yueqian Lin, Zhengmian Hu, Qinsi Wang et al.2025 · 0 citationsarXiv
Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals2506.02281v2 · Qinsi Wang, Jinghan Ke, Hancheng Ye et al.2025 · 0 citationsarXiv
HippoMM: Hippocampal-inspired Multimodal Memory for Long Audiovisual Event Understanding2504.10739v2 · Yueqian Lin, Jingyang Zhang, Qinsi Wang et al.2025 · 1 citationarXiv
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing2503.10742v2 · Yudong Liu, Jingwei Sun, Yueqian Lin et al.2025 · 1 citationarXiv
SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval2412.12009v2 · Yueqian Lin, Yuzhe Fu, Jingyang Zhang et al.2024 · 6 citationsarXiv
Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm2409.07226v2 · Yuning Wu, Jiatong Shi, Yifeng Yu et al.2024 · 2 citationsarXiv
Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey2407.21794v2 · Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang et al.2024 · 4 citationsarXiv
Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and ACE-KiSing2401.17619v3 · Jiatong Shi, Yueqian Lin, Xinyi Bai et al.2024 · 9 citationsarXiv
SD-NAE: Generating Natural Adversarial Examples with Stable Diffusion2311.12981v3 · Yueqian Lin, Jingyang Zhang, Yiran Chen et al.2023 · 4 citationsarXiv
BiSinger: Bilingual Singing Voice Synthesis2309.14089v3 · Huali Zhou, Yueqian Lin, Yao Shi et al.2023 · 1 citationarXiv
RTVis: Research Trend Visualization Toolkit2307.10162v3 · Xingyu Shen, Yueqian Lin, Zhixian Zhang et al.2023 · 1 citationarXiv
OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection2306.09301v5 · Jingyang Zhang, Jingkang Yang, Pengyun Wang et al.2023 · 20 citationsarXiv
In Situ Atomic Force Microscopy Tracking of Nanoparticle Migration in Semicrystalline Polymers.35675165 · Bornani, Kamlesh, Mendez, Nicholas F, Altorbaq, Abdullah S et al.2022 · 7 citationsACS macro letters. 2022;11(6):818-824
Career total: 54 works. 27 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.