Ngai Wong

Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation ACL 2026 NTK-Guided Implicit Neural Teaching CVPR 2026 Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance CVPR 2026 Revisiting Model Interpolation for Efficient Reasoning ACL 2026 DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables CVPR 2025 Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs COLING 2025 GuiLoMo: Allocating Experts and Ranks for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors EMNLP 2025 Hybrid Mesh-Gaussian Representation for Efficient Indoor Scene Reconstruction IJCAI 2025 KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation EMNLP 2025 Nonparametric Teaching for Graph Property Learners ICML 2025 ParallelComp: Parallel Long-Context Compressor for Length Extrapolation ICML 2025 Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency ICCV 2025 Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers IJCAI 2025 QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models EMNLP 2025 Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models COLING 2025 TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review EMNLP 2025 UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective EMNLP 2025 ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference ICLR 2024 Hundred-Kilobyte Lookup Tables for Efficient Single-Image Super-Resolution IJCAI 2024 Learning Spatially Collaged Fourier Bases for Implicit Neural Representation AAAI 2024 LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models NAACL 2024 Mixture-of-Subspaces in Low-Rank Adaptation EMNLP 2024 Nonparametric Teaching of Implicit Neural Representations ICML 2024 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies NeurIPS 2024 Taming Lookup Tables for Efficient Image Retouching ECCV 2024 Weight-Inherited Distillation for Task-Agnostic BERT Compression NAACL 2024 Context-Aware Transformer for 3D Point Cloud Automatic Annotation AAAI 2023 Gradually Excavating External Knowledge for Implicit Complex Question Answering EMNLP 2023 Structured Pruning for Efficient Generative Pre-trained Language Models ACL 2023 Compression of Generative Pre-trained Language Models via Quantization ACL 2022 EZCrop: Energy-Zoned Channels for Robust Output Pruning WACV 2022 FASSST: Fast Attention Based Single-Stage Segmentation Net for Real-Time Instance Segmentation WACV 2022 Multimodal Transformer for Automatic 3D Annotation and Object Detection ECCV 2022 Deformable Butterfly: A Highly Structured and Sparse Linear Transform NeurIPS 2021 S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-Shot Segmentation WACV 2021 Fastened CROWN: Tightened Neural Network Robustness Certificates AAAI 2020 MiSC: Mixed Strategies Crowdsourcing IJCAI 2019 POPQORN: Quantifying Robustness of Recurrent Neural Networks ICML 2019