Profiles2022-2026
Minjoon Seo
KAIST AI
27Papers
13Last author
41Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers27
- The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will ThinkAuthor 12 of 13ICLR 2026 · 6 citations
- Characterizing Pattern Matching and Its Limits on Compositional Task StructuresAuthor 10 of 12ICLR 2026 · 5 citations
- State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal ModelsAuthor 2 of 2AAAI 2026 · 1 citation
- How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?Author 7 of 9ICLR 2025
- Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge AcquisitionAuthor 9 of 9ICLR 2025
- Prometheus: Inducing Fine-Grained Evaluation Capability in Language ModelsAuthor 11 of 13ICLR 2024 · 468 citations
- How Do Large Language Models Acquire Factual Knowledge During Pretraining?Author 7 of 8NeurIPS 2024 · 124 citations
- Aligning to Thousands of Preferences via System Message GeneralizationAuthor 4 of 5NeurIPS 2024 · 102 citations
- Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language ModelsAuthor 10 of 11EMNLP 2024 · 38 citations
- Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained EvaluationAuthor 5 of 5ACL Findings 2024 · 16 citations
- Rethinking the Role of Proxy Rewards in Language Model AlignmentAuthor 2 of 3EMNLP 2024 · 6 citations
- Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained RewardsAuthor 5 of 5EMNLP Findings 2024 · 6 citations
- Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge UtilizationAuthor 4 of 5EMNLP 2024 · 3 citations
- Exploring the Practicality of Generative Retrieval on Dynamic CorporaAuthor 6 of 6EMNLP 2024 · 1 citation
- On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and ReasoningAuthor 2 of 2EMNLP 2024
- Semiparametric Token-Sequence Co-SupervisionAuthor 7 of 7ACL 2024
- The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-TuningAuthor 7 of 7EMNLP 2023 · 45 citations
- Aligning Large Language Models through Synthetic FeedbackAuthor 7 of 9EMNLP 2023 · 13 citations
- Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersAuthor 5 of 5ICLR 2023 · 10 citations
- Nonparametric Decoding for Generative RetrievalAuthor 8 of 8ACL Findings 2023 · 9 citations
- Towards standardizing Korean Grammatical Error Correction: Datasets and AnnotationAuthor 6 of 7ACL 2023 · 6 citations
- ClaimDiff: Comparing and Contrasting Claims on Contentious IssuesAuthor 6 of 6ACL Findings 2023 · 1 citation
- Two Examples are Better than One: Context Regularization for Gradient-based Prompt TuningAuthor 4 of 6ACL Findings 2023 · 1 citation
- Fixed Input Parameterization for Efficient PromptingAuthor 5 of 7ACL Findings 2023
- Towards Continual Knowledge Learning of Language ModelsAuthor 8 of 8ICLR 2022 · 204 citations
- TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language ModelsAuthor 8 of 9EMNLP 2022 · 42 citations
- Generative Multi-hop RetrievalAuthor 4 of 4EMNLP 2022 · 12 citations
