Sledovať
Heming Xia
Heming Xia
Ďalšie mená夏 鹤明
Natural Language Processing Group, The Hong Kong Polytechnic University
Overená e-mailová adresa na: connect.polyu.hk - Domovská stránka
Názov
Citované v
Citované v
Rok
A survey on in-context learning
Q Dong, L Li, D Dai, C Zheng, J Ma, R Li, H Xia, J Xu, Z Wu, B Chang, ...
EMNLP 2024, 2024
15542024
Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation
H Xia, T Ge, P Wang, SQ Chen, F Wei, Z Sui
EMNLP 2023 Findings, 2022
76*2022
Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding
H Xia, Z Yang, Q Dong, P Wang, Y Li, T Ge, T Liu, W Li, Z Sui
ACL 2024 Findings, 2024
722024
Improved deep learning techniques in gravitational-wave data analysis
H Xia, L Shao, J Zhao, Z Cao
Phys. Rev. D 103, 024-040, 2021
372021
Lossless acceleration for Seq2seq generation with aggressive decoding
T Ge, H Xia, X Sun, SQ Chen, F Wei
Microsoft Research Technical Report, 2022
192022
Enhancing Continual Relation Extraction via Classifier Decomposition
H Xia, P Wang, T Liu, B Lin, Y Cao, Z Sui
ACL 2023 Findings, 2023
152023
Premise-based multimodal reasoning: Conditional inference on joint textual and visual clues
Q Dong, Z Qin, H Xia, T Feng, S Tong, H Meng, L Xu, W Zhan, S Li, Z Wei, ...
ACL 2022, 2021
102021
Enhancing Tool Retrieval with Iterative Feedback from Large Language Models
Q Xu, Y Li, H Xia, W Li
EMNLP 2024 Findings, 2024
72024
ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories
H Xia, Q Dong, L Li, J Xu, T Liu, Z Qin, Z Sui
EMNLP 2023 Findings, 2023
62023
Can Large Multimodal Models Uncover Deep Semantics Behind Images?
Y Yang, Z Li, Q Dong, H Xia, Z Sui
ACL 2024 Findings, 2024
52024
AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction
H Wang, R Wang, B Xue, H Xia, J Cao, Z Liu, JZ Pan, KF Wong
EMNLP 2024, 2024
12024
Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens
W Luo, S Zheng, H Xia, W Wang, Y Lei, T Liu, S Chen, Z Sui
EMNLP 2024 Findings, 2024
12024
Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization
S Tong, H Xia, D Dai, R Xu, T Liu, B Lin, Y Cao, Z Sui
EMNLP 2023 Findings, 2023
1*2023
How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation
R Li, H Xia, X Yuan, Q Dong, L Sha, W Li, Z Sui
arXiv preprint arXiv:2502.14642, 2025
2025
Beyond Single Frames: Can LMMs Comprehend Temporal and Contextual Narratives in Image Sequences?
X Wang, H Xia, J Song, L Guan, Y Yang, Q Dong, W Luo, Y Pu, Y Wang, ...
arXiv preprint arXiv:2502.13925, 2025
2025
TokenSkip: Controllable Chain-of-Thought Compression in LLMs
H Xia, Y Li, CT Leong, W Wang, W Li
arXiv preprint arXiv:2502.12067, 2025
2025
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
H Xia, Y Li, J Zhang, C Du, W Li
ICLR 2025, 2024
2024
Lookers-On See Most of the Game: An External Insight-Guided Method for Enhancing Uncertainty Estimation
R Li, J Long, M Qi, L Sha, P Wang, H Xia, Z Sui
2024
Systém momentálne nemôže vykonať operáciu. Skúste to neskôr.
Články 1–18