PPaperPicks

Minjoon Seo

31 papers at tracked venues · 17 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
  2. Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact
  3. State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models
  4. Generative Prompt Internalization
  5. How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
  6. Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition
  7. Latent Action Pretraining from Videos
  8. Reasoning Models Better Express Their Confidence
  9. RouterRetriever: Routing over a Mixture of Expert Embedding Models
  10. The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models
  11. Towards Reliable and Practical Phishing Detection
  12. Aligning Large Language Models by On-Policy Self-Judgment
  13. Aligning to Thousands of Preferences via System Message Generalization
  14. Exploring the Practicality of Generative Retrieval on Dynamic Corpora
  15. FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
  16. Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization
  17. How Do Large Language Models Acquire Factual Knowledge During Pretraining?
  18. How Well Do Large Language Models Truly Ground?
  19. Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following
  20. KTRL+F: Knowledge-Augmented In-Document Search
  21. LangBridge: Multilingual Reasoning Without Multilingual Supervision
  22. On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning
  23. Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models
  24. Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation
  25. Prometheus: Inducing Fine-Grained Evaluation Capability in Language Models
  26. REPLUG: Retrieval-Augmented Black-Box Language Models
  27. Rethinking the Role of Proxy Rewards in Language Model Alignment
  28. Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards
  29. Semiparametric Token-Sequence Co-Supervision
  30. SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
  31. Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision