Profiles2020-2026
Lu Hou
Huawei Technologies Co., Ltd.
19Papers
4Last author
51Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers19
- Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection SuppressionAuthor 6 of 6AAAI 2026 · 21 citations
- EMOVA: Empowering Language Models to See, Hear and Speak with Vivid EmotionsAuthor 30 of 31CVPR 2025
- TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video UnderstandingAuthor 5 of 5CVPR 2024 · 83 citations
- TempCompass: Do Video LLMs Really Understand Videos?Author 9 of 9ACL Findings 2024 · 45 citations
- IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens IntactAuthor 7 of 9ACL Findings 2024 · 13 citations
- Adaptive Low-Precision Training for Embeddings in Click-Through Rate PredictionAuthor 3 of 8AAAI 2023 · 27 citations
- TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language UnderstandingAuthor 5 of 5EMNLP Findings 2023 · 20 citations
- mCLIP: Multilingual CLIP via Cross-lingual TransferAuthor 2 of 9ACL 2023 · 13 citations
- Structured Pruning for Efficient Generative Pre-trained Language ModelsAuthor 2 of 8ACL Findings 2023 · 13 citations
- Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document UnderstandingAuthor 10 of 13ACL 2023 · 3 citations
- Compression of Generative Pre-trained Language Models via QuantizationAuthor 2 of 8ACL 2022 · 119 citations
- Towards Efficient Post-training Quantization of Pre-trained Language ModelsAuthor 2 of 6NeurIPS 2022 · 62 citations
- LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal ModelingAuthor 3 of 6EMNLP 2022 · 11 citations
- Improved OOD Generalization via Adversarial Training and PretraingAuthor 2 of 7ICML 2021 · 99 citations
- Reweighting Augmented Samples by Minimizing the Maximal Expected LossAuthor 2 of 6ICLR 2021 · 25 citations
- BinaryBERT: Pushing the Limit of BERT QuantizationAuthor 3 of 9ACL 2021
- GhostBERT: Generate More Features with Cheap Operations for BERTAuthor 2 of 6ACL 2021
- DynaBERT: Dynamic BERT with Adaptive Width and DepthAuthor 1 of 6NeurIPS 2020 · 401 citations
- TernaryBERT: Distillation-aware Ultra-low Bit BERTAuthor 2 of 7EMNLP 2020 · 147 citations
