Lune

Profiles2025-2026

Jaeyoung Do

Seoul National University

14Papers
13Last author
16Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers14

  1. RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning ModelsAuthor 3 of 3ICLR 2026 · 10 citations
  2. Revisiting Filtered ANN Benchmarks: A Hardness-Controlled Benchmark Generator for Realistic EvaluationAuthor 4 of 4VLDB 2026 · 2 citations
  3. VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal SegmentationAuthor 2 of 2CVPR 2026 · 2 citations
  4. MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-raysAuthor 3 of 3ACL Findings 2026 · 1 citation
  5. MATA: Multi-Agent Framework for Reliable and Flexible Table Question AnsweringAuthor 4 of 4ACL Findings 2026
  6. MatKV: Trading Compute for Flash Storage in LLM InferenceAuthor 5 of 6ICDE 2026
  7. Medic-AD: Towards Medical Vision-Language Model's Clinical IntelligenceAuthor 10 of 10CVPR 2026
  8. Unified Static-Dynamic Pruning for Efficient LLM InferenceAuthor 3 of 3VLDB 2026
  9. VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language ModelsAuthor 4 of 4ICML 2026
  10. Turbocharging Vector Databases using Modern SSDsAuthor 4 of 4VLDB 2025 · 13 citations
  11. MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-FormulaAuthor 7 of 7AAAI 2025 · 7 citations
  12. Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep AllocationAuthor 2 of 2NeurIPS 2025 · 2 citations
  13. Exploring and Leveraging Class Vectors for Classifier EditingAuthor 2 of 2NeurIPS 2025 · 1 citation
  14. SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive DecodingAuthor 4 of 4ICML 2025
Dusk over the sea between two cliffs drawn in fine vertical lines