Xiang Liu

Orcid: 0009-0003-2639-1804

Affiliations:
  • Hong Kong University of Science and Technology, Guang Zhou, China


According to our database1, Xiang Liu authored at least 45 papers between 2014 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
NestedKV: Nested Memory Routing for Long-Context KV Cache Compression.
CoRR, May, 2026

Position: LLM Inference Should Be Evaluated as Energy-to-Token Production.
CoRR, May, 2026

MDN: Parallelizing Stepwise Momentum for Delta Linear Attention.
CoRR, May, 2026

Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph.
CoRR, March, 2026

Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling.
CoRR, February, 2026

SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching.
CoRR, January, 2026

2025
DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference.
CoRR, October, 2025

Reasoning Language Model Inference Serving Unveiled: An Empirical Study.
CoRR, October, 2025

AnTKV: Anchor Token-Aware Sub-Bit Vector Quantization for KV Cache in Large Language Models.
CoRR, June, 2025

FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management.
CoRR, May, 2025

SSR: Speculative Parallel Scaling Reasoning in Test-time.
CoRR, May, 2025

CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring.
CoRR, May, 2025

The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?
CoRR, February, 2025

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models.
CoRR, February, 2025

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing.
CoRR, February, 2025

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?
CoRR, February, 2025

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference.
CoRR, February, 2025

City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

ParZC: Parametric Zero-Cost Proxies for Efficient NAS.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024
ParZC: Parametric Zero-Cost Proxies for Efficient NAS.
CoRR, 2024

Should We Really Edit Language Models? On the Evaluation of Edited Language Models.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

3D Question Answering for City Scene Understanding.
Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

LongGenBench: Long-context Generation Benchmark.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

LPZero: Language Model Zero-cost Proxy Search from Zero.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023
Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models.
CoRR, 2023

2022
Deep learning based solder joint defect detection on industrial printed circuit board X-ray images.
Complex Intell. Syst., 2022

2021
Time-Series Regeneration With Convolutional Recurrent Generative Adversarial Network for Remaining Useful Life Estimation.
IEEE Trans. Ind. Informatics, 2021

2020
Deep Learning Based Defect Detection for Solder Joints on Industrial X-Ray Circuit Board Images.
Proceedings of the 18th IEEE International Conference on Industrial Informatics, 2020

2019
An Experimental Study for Tracking Crowd in Smart Cities.
IEEE Syst. J., 2019

Robot Control in Human Environment using Deep Reinforcement Learning and Convolutional Neural Network.
Proceedings of the 2019 IEEE International Conference on Robotics and Biomimetics, 2019

2018
Understanding crowd density with a smartphone sensing system.
Proceedings of the 4th IEEE World Forum on Internet of Things, 2018

2017
Indoor positioning using similarity-based sequence and dead reckoning without training.
Proceedings of the 18th IEEE International Workshop on Signal Processing Advances in Wireless Communications, 2017

Cooperative relative positioning of mobile users by fusing IMU inertial and UWB ranging information.
Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

2016
System design of the internet of things for residential smart grid.
IEEE Wirel. Commun., 2016

Design of Cloud-Connected IoT System for Smart Buildings on Energy Management (Invited paper).
EAI Endorsed Trans. Ind. Networks Intell. Syst., 2016

SenseFlow: An Experimental Study for Tracking People.
CoRR, 2016

Selective AP-Sequence Based Indoor Localization without Site Survey.
Proceedings of the IEEE 83rd Vehicular Technology Conference, 2016

Relative Positioning by Fusing Signal Strength and Range Information in a Probabilistic Framework.
Proceedings of the 2016 IEEE Globecom Workshops, Washington, DC, USA, December 4-8, 2016, 2016

2015
Demand Response Management for Residential Smart Grid: From Theory to Practice.
IEEE Access, 2015

2014
Smart Tourist - Passive Mobility Tracking Through Mobile Application.
Proceedings of the Internet of Things. IoT Infrastructures, 2014


  Loading...