Chuan Wu

24 papers · 2019–2026 · 10 conferences · across top CS/AI conferences

Achievements

+13 more ↓

🌍 Conference Polyglot (10) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (6)

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏃 Academic Marathon (6) 🤝 Dynamic Duo (10) 🏆 Grand Slam 🧬 Topic Evolution 🏆 Keyword Champion (2) 🔥 Unstoppable (5) ⚡ Prolific Year (5) 🗃️ Keyword Collector (94) ❓ The Questioner 💎 Century Club (22) 🚀 Conference Pioneer

Conferences

ACL (4) EMNLP (4) AAAI (3) ICLR (3) ICML (3) NIPS (2) NSDI (2) ECCV (1) ICCV (1) NAACL (1)

Top co-authors

Lingpeng Kong (10) Sheng wang (9) Jiyue Jiang (8) Liheng Chen (5) Junwei Su (5) Pengan CHEN (4) Yanghua Peng (3) Boyang Xue (3) Jiahui Gao (3) Xin Jiang (2)

Research topics

Applications (1)

Keywords

large language model (6) model compression (3) distributed training (3) parameter-efficient fine-tuning (2) dialogue system (2) graph neural network (2) multimodal large language model (2) low-resource language (2) cantonese language (2) parameter-efficient finetuning (2) cognitive stimulation (2) low-rank adaptation (2) language model training (1) text generation (1) self-attention mechanism (1) in-context learning (1) multilingual nlp (1) neural network training (1) transformer architecture (1) knowledge distillation (1)

Papers

A Principle-Driven Adaptive Policy for Group Cognitive Stimulation Dialogue for Elderly with Cognitive Impairment AAAI 2026 MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference ACL 2026 How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models NAACL 2025 QSpec: Speculative Decoding with Complementary Quantization Schemes EMNLP 2025 On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks ICML 2025 Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models EMNLP 2025 Unveiling Multimodal Processing: Exploring Activation Patterns in Multimodal LLMs for Interpretability and Efficiency EMNLP 2025 ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development NSDI 2025 Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration ICLR 2025 MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards ICLR 2025 A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations ICML 2025 ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom EMNLP 2025 PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA ACL 2024 LoRA Meets Dropout under a Unified Framework ACL 2024 On the Topology Awareness and Generalization Performance of Graph Neural Networks ECCV 2024 Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models NIPS 2024 PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks ICLR 2024 MixSynthFormer: A Transformer Encoder-like Structure with Mixed Synthetic Self-attention for Efficient Human Pose Estimation ICCV 2023 A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment ACL 2023 Towards Robust Graph Incremental Learning on Evolving Graphs ICML 2023 BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing NSDI 2023 SAPipe: Staleness-Aware Pipeline for Data Parallel DNN Training NIPS 2022 Distributed Machine Learning through Heterogeneous Edge Systems AAAI 2020 Learning Resource Allocation and Pricing for Cloud Profit Maximization AAAI 2019