Wei Tao
Publications
- WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization (2026), In TACO2026 (CCF-A)
- Triage: Hierarchical Visual Budgeting for Efficient Video Reasoning in Vision-Language Models (2026), In ICASSP2026 (CCF-B)
- Vista: Scene-Aware Optimization for Streaming Video Question Answering under Post-Hoc Queries (2025), In AAAI2026 (CCF-A)
- MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts (2025), In ACL2025 (CCF-A)
- BAGNet: A Boundary-Aware Graph Attention Network for 3D Point Cloud Semantic Segmentation (2025), In IJCNN2025 (CCF-C)
- MADLLM: Multivariate Anomaly Detection via Pre-trained LLMs (2025), In ICME2025 (CCF-B)
- PointActionCLIP: Preventing Transfer Degradation in Point Cloud Action Recognition with a Triple-Path CLIP (2025), In ICASSP2025 (CCF-B)
- Cocktail:Chunk-AdaptiveMixed-Precision Ouanization for Long-Context LLM inference (2025), In DATE2025 (CCF-B) Best Paper Award
- Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers (2024), In DATE2024 (CCF-B)
- QSpeech: Low-Qubit Quantum Speech Application Toolkit (2022), In IJCNN2022 (CCF-C)