Lu Hou

papers

1,309

total citations

papers (13)

TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding

CVPR 2024arXiv

372

citations

DynaBERT: Dynamic BERT with Adaptive Width and Depth

NEURIPS 2020arXiv

364

citations

Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark

NEURIPS 2022arXiv

138

citations

FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation

NEURIPS 2023arXiv

110

citations

Towards Efficient Post-training Quantization of Pre-trained Language Models

NEURIPS 2022arXiv

citations

VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models

ECCV 2024arXiv

citations

MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric

CVPR 2024arXiv

citations

Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models

COLM 2025arXiv

citations

HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models

CVPR 2025arXiv

citations

OAC: Output-adaptive Calibration for Accurate Post-training Quantization

AAAI 2025arXiv

citations

Lu Hou

papers (13)

TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding

DynaBERT: Dynamic BERT with Adaptive Width and Depth

Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark

FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation

Towards Efficient Post-training Quantization of Pre-trained Language Models

VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance

FlatQuant: Flatness Matters for LLM Quantization

MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric

Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models

HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models

OAC: Output-adaptive Calibration for Accurate Post-training Quantization

papers (13)

TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding

DynaBERT: Dynamic BERT with Adaptive Width and Depth

Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark

FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation

Towards Efficient Post-training Quantization of Pre-trained Language Models

VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance

FlatQuant: Flatness Matters for LLM Quantization

MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric

Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models

HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models

OAC: Output-adaptive Calibration for Accurate Post-training Quantization