PPaperPicks

Se-Young Yun

Korea Advanced Institute of Science and Technology (KAIST), Graduate School of AI Korea, Daejeon, South Korea

36 papers at tracked venues · 28 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. MERIT Feedback Elicits Better Bargaining in LLM Negotiators
  2. Multi-Drafter Speculative Decoding with Alignment Feedback
  3. Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses
  4. AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
  5. Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models
  6. C²: Scalable Auto-Feedback for LLM-based Chart Generation
  7. DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
  8. Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems
  9. Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators
  10. FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning
  11. KLASS: KL-Guided Fast Inference in Masked Diffusion Models
  12. MA2E: Addressing Partial Observability in Multi-Agent Reinforcement Learning with Masked Auto-Encoder
  13. MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation
  14. Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
  15. MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition
  16. Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation
  17. QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval
  18. Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model
  19. Self-Training Elicits Concise Reasoning in Large Language Models
  20. A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
  21. An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints
  22. BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization
  23. Block Transformer: Global-to-Local Language Modeling for Fast Inference
  24. Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models
  25. Conditional Synthesis of 3D Molecules with Time Correction Sampler
  26. DistiLLM: Towards Streamlined Distillation for Large Language Models
  27. FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning
  28. Fine-tuning Pre-trained Models for Robustness under Noisy Labels
  29. Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
  30. Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
  31. Leveraging Normalization Layer in Adapters with Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning
  32. Preference Alignment with Flow Matching
  33. Stable Language Model Pre-training by Reducing Embedding Variability
  34. Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs
  35. Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models
  36. Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters