Profiles2022-2026
Jaeho Lee
HJ AILAB
14Papers
6Last author
17Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers14
- Speculative End-Turn Detector for Efficient Speech Chatbot AssistantAuthor 3 of 4ACL 2026 · 5 citations
- Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language ModelsAuthor 2 of 2ACL Findings 2026
- Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in GeneralizationAuthor 3 of 3ICML 2026
- Fast Training of Sinusoidal Neural Fields via Scaling InitializationAuthor 3 of 3ICLR 2025
- Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language ModelsAuthor 3 of 5ACL Findings 2025
- Prompt-based Depth Pruning of Large Language ModelsAuthor 3 of 3ICML 2025
- ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language ModelsAuthor 4 of 6ICLR 2025
- Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual FidelityAuthor 6 of 6ICML 2024 · 25 citations
- Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model QuantizationAuthor 5 of 6EMNLP 2024 · 6 citations
- Hybrid Neural Representations for Spherical DataAuthor 3 of 4ICML 2024 · 3 citations
- Decoding with Limited Teacher Supervision Requires Understanding When to Trust the TeacherAuthor 3 of 3EMNLP 2024
- Learning Large-scale Neural Fields via Context Pruned Meta-LearningAuthor 4 of 6NeurIPS 2023 · 16 citations
- Scalable Neural Video Representations with Learnable Positional FeaturesAuthor 3 of 4NeurIPS 2022 · 47 citations
- Meta-Learning with Self-Improving Momentum TargetAuthor 4 of 5NeurIPS 2022 · 17 citations
