HL
Hai Helen Li
cs.LGcs.CVcs.AIcs.ARstat.MLcs.NEcs.CReess.AScs.DCcs.SD
On Valency
published · living versionsW_macrk6t4·v1 · currentpublished
InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
with Qinsi Wang, Wei Wen, Chong Zhou, Saksham Suri +5
1 version
W_jm3vhkc9·v1published
Preprints & journals
124 papers in the corpus · 2012–2026Will 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
EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture2605.24144v1 · Bowen Duan, Cong Guo, Chiyue Wei et al.2026 · 0 citationsarXiv
Skilled AI Agents for Embedded and IoT Systems Development2603.19583v1 · Yiming Li, Yuhan Cheng, Mingchen Ma et al.2026 · 0 citationsarXiv
Recognition method for the flight parameters of multiple projectiles with light-screen array sensor.41455720 · Li, Jing, Ni, Jinping, Tian, Hui et al.2026 · 2 citationsScientific reports. 2025;16(1):3212
CAMformer: Associative Memory is All You Need2511.19740v1 · Tergel Molom-Ochir, Benjamin F. Morris, Mark Horton 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
Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap2509.26542v1 · Yueqian Lin, Zhengmian Hu, Qinsi Wang et al.2025 · 0 citationsarXiv
MulPi: A Multi-class and Patient-Independent Epileptic Seizure Classifier With Co-Designed Input-stationary Computing-in-SRAM.40512641 · Kim, Bokyung, Huang, Qijia, Taylor, Brady et al.2025 · 5 citationsIEEE transactions on biomedical circuits and systems. 2025;19(4):756-766
OASIS: Outlier-Aware LUT-Based GEMM with Dual-Side Quantization for LLM Inference Acceleration2507.23035v4 · Xueying Wu, Baijun Zhou, Zhihui Gao et al.2025 · 0 citations2026 ACM/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA), pp. 307-321
SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues2506.00668v1 · Martin Kuo, Jianyi Zhang, Aolin Ding et al.2025 · 0 citationsarXiv
Phi: Leveraging Pattern-based Hierarchical Sparsity for High-Efficiency Spiking Neural Networks2505.10909v1 · Chiyue Wei, Bowen Duan, Cong Guo et al.2025 · 9 citationsarXiv
AutoRAC: Automated Processing-in-Memory Accelerator Design for Recommender Systems2505.10748v1 · Feng Cheng, Tunhou Zhang, Junyao Zhang et al.2025 · 2 citationsarXiv
Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-aware Cache Compression2505.06901v1 · Feng Cheng, Cong Guo, Chiyue Wei et al.2025 · 12 citationsarXiv
Transitive Array: An Efficient GEMM Accelerator with Result Reuse2504.16339v1 · Cong Guo, Chiyue Wei, Jiaming Tang et al.2025 · 8 citationsarXiv
Elucidating Compound Mechanism of Action and Polypharmacology with a Large-scale Perturbational Profile Compendium.37873470 · Hu, Lucas ZhongMing, Hirschhorn, Tal, Douglass, Eugene et al.2026 · 1 citationbioRxiv : the preprint server for biology. 2025
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
Prosperity: Accelerating Spiking Neural Networks via Product Sparsity2503.03379v2 · Chiyue Wei, Cong Guo, Feng Cheng et al.2025 · 14 citationsarXiv
SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval2412.12009v2 · Yueqian Lin, Yuzhe Fu, Jingyang Zhang et al.2024 · 6 citationsarXiv
LoBAM: LoRA-Based Backdoor Attack on Model Merging2411.16746v4 · Ming Yin, Jingyang Zhang, Jingwei Sun et al.2024 · 0 citationsarXiv
Towards Automated Model Design on Recommender Systems2411.07569v1 · Tunhou Zhang, Dehua Cheng, Yuchen He et al.2024 · 2 citationsACM Transactions on Recommender Systems (TORS) 2024
qGDP: Quantum Legalization and Detailed Placement for Superconducting Quantum Computers2411.02447v1 · Junyao Zhang, Guanglei Zhou, Feng Cheng et al.2024 · 0 citationsarXiv
A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models2410.07265v1 · Cong Guo, Feng Cheng, Zhixu Du et al.2024 · 32 citationsarXiv
FedProphet: Memory-Efficient Federated Adversarial Training via Robust and Consistent Cascade Learning2409.08372v2 · Minxue Tang, Yitu Wang, Jingyang Zhang et al.2024 · 0 citationsarXiv
MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning2409.06067v3 · Jianyi Zhang, Hao Frank Yang, Ang Li et al.2024 · 8 citationsIEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)
MonoSparse-CAM: Efficient Tree Model Processing via Monotonicity and Sparsity in CAMs2407.11071v2 · Tergel Molom-Ochir, Brady Taylor, Hai Li (Helen) et al.2024 · 1 citationarXiv
Multi-agent Cooperative Games Using Belief Map Assisted Training2406.19477v1 · Qinwei Huang, Chen Luo, Alex B. Wu et al.2024 · 2 citationsECAI 2023. IOS Press, 2023: 1617-1624
Can Dense Connectivity Benefit Outlier Detection? An Odyssey with NAS2406.01975v1 · Hao Fu, Tunhou Zhang, Hai Li et al.2024 · 0 citationsarXiv
CSCO: Connectivity Search of Convolutional Operators2404.17152v2 · Tunhou Zhang, Shiyu Li, Hsin-Pai Cheng et al.2024 · 0 citationsarXiv
Do Counterfactual Examples Complicate Adversarial Training?2404.10588v2 · Eric Yeats, Cameron Darwin, Eduardo Ortega et al.2024 · 0 citationsarXiv
Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models2403.20331v4 · Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang et al.2024 · 4 citationsarXiv
Vox-Fusion++: Voxel-based Neural Implicit Dense Tracking and Mapping with Multi-maps2403.12536v1 · Hongjia Zhai, Hai Li, Xingrui Yang et al.2024 · 5 citationsarXiv
Qplacer: Frequency-Aware Component Placement for Superconducting Quantum Computers2401.17450v3 · Junyao Zhang, Hanrui Wang, Qi Ding et al.2024 · 2 citationsarXiv
Adversarial Estimation of Topological Dimension with Harmonic Score Maps2312.06869v1 · Eric Yeats, Cameron Darwin, Frank Liu et al.2023 · 0 citationsarXiv
NDSEARCH: Accelerating Graph-Traversal-Based Approximate Nearest Neighbor Search through Near Data Processing2312.03141v2 · Yitu Wang, Shiyu Li, Qilin Zheng et al.2023 · 28 citationsarXiv
EDALearn: A Comprehensive RTL-to-Signoff EDA Benchmark for Democratized and Reproducible ML for EDA Research2312.01674v2 · Jingyu Pan, Chen-Chia Chang, Zhiyao Xie et al.2023 · 4 citationsarXiv
SD-NAE: Generating Natural Adversarial Examples with Stable Diffusion2311.12981v3 · Yueqian Lin, Jingyang Zhang, Yiran Chen et al.2023 · 4 citationsarXiv
Farthest Greedy Path Sampling for Two-shot Recommender Search2310.20705v1 · Yufan Cao, Tunhou Zhang, Wei Wen et al.2023 · 0 citationsarXiv
SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models2310.18859v2 · Zhixu Du, Shiyu Li, Yuhao Wu et al.2023 · 5 citationsSeventh Conference on Machine Learning and Systems, (2024)
Block-Wise Mixed-Precision Quantization: Enabling High Efficiency for Practical ReRAM-based DNN Accelerators2310.12182v3 · Xueying Wu, Edward Hanson, Nansu Wang et al.2023 · 16 citationsarXiv
Zero-Shot Emotion Transfer For Cross-Lingual Speech Synthesis2310.03963v1 · Yuke Li, Xinfa Zhu, Yi Lei et al.2023 · 6 citationsarXiv
Stable and Causal Inference for Discriminative Self-supervised Deep Visual Representations2308.08321v1 · Yuewei Yang, Hai Li, Yiran Chen2023 · 2 citationsarXiv
OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection2306.09301v5 · Jingyang Zhang, Jingkang Yang, Pengyun Wang et al.2023 · 20 citationsarXiv
FLSL: Feature-level Self-supervised Learning2306.06203v4 · Qing Su, Anton Netchaev, Hai Li et al.2023 · 0 citationsarXiv
SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection2303.14531v1 · Jingyang Zhang, Nathan Inkawhich, Randolph Linderman et al.2023 · 0 citationsarXiv
Disentangling Learning Representations with Density Estimation2302.04362v1 · Eric Yeats, Frank Liu, Hai Li2023 · 0 citationsarXiv
GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning2301.13465v1 · Xin Dong, Ruize Wu, Chao Xiong et al.2023 · 7 citationsProceedings of the 31st ACM International Conference on Information & Knowledge Management. 2022: 386-395
HCE: Improving Performance and Efficiency with Heterogeneously Compressed Neural Network Ensemble2301.07794v1 · Jingchi Zhang, Huanrui Yang, Hai Li2023 · 0 citationsarXiv
Explainable Alzheimer's Disease Detection Using Linguistic Features from Automatic Speech Recognition.37433284 · Tang, Lijuan, Zhang, Zhenglin, Feng, Feifan et al.2023 · 7 citationsDementia and geriatric cognitive disorders. 2023;52(4):240-248
Low-Altitude Windshear Wind Speed Estimation Method Based on KASPICE-STAP.36616650 · Li, Hai, Chen, Yutong, Feng, Kaihong et al.2023 · 1 citationSensors (Basel, Switzerland). 2022;23(1)
Rethinking Normalization Methods in Federated Learning2210.03277v1 · Zhixu Du, Jingwei Sun, Ang Li et al.2022 · 25 citationsarXiv
Career total: at least 662 works. 124 are in this corpus.Showing the 50 most recent.
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.