Lu Hou

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models CVPR 2026 DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning CVPR 2026 Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression AAAI 2026 Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving CVPR 2026 Efficient Inference for Large Language Models –Algorithm, Model, and System EMNLP 2025 EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions CVPR 2025 Faster and Better LLMs via Latency-Aware Test-Time Scaling EMNLP 2025 FlatQuant: Flatness Matters for LLM Quantization ICML 2025 HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models CVPR 2025 ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance ICCV 2025 OAC: Output-adaptive Calibration for Accurate Post-training Quantization AAAI 2025 Extending Context Window of Large Language Models via Semantic Compression ACL 2024 IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact ACL 2024 MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric CVPR 2024 Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models ICLR 2024 TempCompass: Do Video LLMs Really Understand Videos? ACL 2024 TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding CVPR 2024 UNIT: Unifying Image and Text Recognition in One Vision Encoder NeurIPS 2024 Visually Guided Generative Text-Layout Pre-training for Document Intelligence NAACL 2024 VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models ECCV 2024 Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction AAAI 2023 FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation NeurIPS 2023 mCLIP: Multilingual CLIP via Cross-lingual Transfer ACL 2023 Structured Pruning for Efficient Generative Pre-trained Language Models ACL 2023 TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding EMNLP 2023 Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding ACL 2023 Compression of Generative Pre-trained Language Models via Quantization ACL 2022 Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation ACL 2022 FILIP: Fine-grained Interactive Language-Image Pre-Training ICLR 2022 LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling EMNLP 2022 Towards Efficient Post-training Quantization of Pre-trained Language Models NeurIPS 2022 Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark NeurIPS 2022 BinaryBERT: Pushing the Limit of BERT Quantization ACL 2021 GhostBERT: Generate More Features with Cheap Operations for BERT ACL 2021 Improved OOD Generalization via Adversarial Training and Pretraing ICML 2021 Reweighting Augmented Samples by Minimizing the Maximal Expected Loss ICLR 2021 DynaBERT: Dynamic BERT with Adaptive Width and Depth NeurIPS 2020 TernaryBERT: Distillation-aware Ultra-low Bit BERT EMNLP 2020 Analysis of Quantized Models ICLR 2019 Normalization Helps Training of Quantized LSTM NeurIPS 2019 Loss-aware Weight Quantization of Deep Networks ICLR 2018