Steven Hoi

32 papers · 2013–2026 · 12 conferences · across top CS/AI conferences

Achievements

+12 more ↓

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🗺️ Taxonomy Completionist (10) 🌍 Conference Polyglot (12)

🌈 Renaissance Researcher (7) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 👥 Mega-Team (23) 🧬 Topic Evolution 🏆 Keyword Champion (2) 🗃️ Keyword Collector (84) ⚡ Prolific Year (7) 📈 Trend Setter 💎 Century Club (31) 🔥 Unstoppable (6) ❓ The Questioner

Conferences

ICLR (10) EMNLP (4) ACL (3) ACML (3) ICML (3) NAACL (3) CVPR (1) ECCV (1) IJCNLP (1) INTERSPEECH (1) JMLR (1) UAI (1)

Top co-authors

Junnan Li (9) Doyen Sahoo (8) Chenghao Liu (7) Caiming Xiong (7) Hung Le (5) Quang Pham (4) Gerald Woo (3) DONGXU LI (3) Silvio Savarese (3) Shafiq Joty (3)

Keywords

multimodal learning (6) large language model (4) code generation (3) transfer learning (3) zero-shot learning (3) video understanding (3) visual question answering (3) transformer network (2) anomaly detection (2) online learning (2) dialogue system (2) vision-language pre-training (2) vision-language model (2) data stream mining (2) video-grounded dialogue (2) time series forecasting (2) self-supervised learning (1) benchmark evaluation (1) collaborative filtering (1) representation learning (1)

Papers

MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments ACL 2026 What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases NAACL 2024 Masked Unsupervised Self-training for Label-free Image Classification ICLR 2023 From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models CVPR 2023 Merlion: End-to-End Machine Learning for Time Series JMLR 2023 CodeT5+: Open Code Large Language Models for Code Understanding and Generation EMNLP 2023 HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts EMNLP 2023 Personalized Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation EMNLP 2023 Towards Low-Resource Automatic Program Repair with Meta-Learning and Pretrained Language Models EMNLP 2023 Learning Deep Time-index Models for Time Series Forecasting ICML 2023 BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models ICML 2023 Learning Fast and Slow for Online Time Series Forecasting ICLR 2023 BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation ICML 2022 CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting ICLR 2022 Multimodal Dialogue State Tracking NAACL 2022 VGNMN: Video-grounded Neural Module Networks for Video-Grounded Dialogue Systems NAACL 2022 Continual Normalization: Rethinking Batch Normalization for Online Continual Learning ICLR 2022 MoPro: Webly Supervised Learning with Momentum Prototypes ICLR 2021 Prototypical Contrastive Learning of Unsupervised Representations ICLR 2021 Contextual Transformation Networks for Online Continual Learning ICLR 2021 Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues ICLR 2021 PolarNet: Learning to Optimize Polar Keypoints for Keypoint Based Object Detection ICLR 2021 Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition INTERSPEECH 2021 Task similarity aware meta learning: theory-inspired improvement on MAML UAI 2021 Tree-Structured Attention with Hierarchical Accumulation ICLR 2020 The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation ECCV 2020 Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems ACL 2019 Cost Sensitive Online Multiple Kernel Classification ACML 2016 SOLAR: Scalable Online Learning Algorithms for Ranking IJCNLP 2015 SOLAR: Scalable Online Learning Algorithms for Ranking ACL 2015 Online Passive Aggressive Active Learning and Its Applications ACML 2014 Second Order Online Collaborative Filtering ACML 2013