pith. sign in

Yushun Dong

Identifiers

  • name variant Yushun Dong 0.60 · backfill

Papers (17)

  1. EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering cs.CL · 2026 · author #6
  2. Closing the Loop on Latent Reasoning via Test-Time Reconstruction cs.AI · 2026 · author #6
  3. An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic cs.CR · 2026 · author #3
  4. TIGER: Traceable Inference with Graph-Based Evidence Routing for Mitigating Hallucinations in Multimodal Generation cs.AI · 2026 · author #5
  5. Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks? cs.LG · 2026 · author #4
  6. Does Your Wildfire Prediction Model Actually Work, or Just Score Well? cs.LG · 2026 · author #5
  7. GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It? cs.CR · 2026 · author #5
  8. SOMA: Efficient Multi-turn LLM Serving via Small Language Model cs.CL · 2026 · author #6
  9. LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer? cs.AI · 2026 · author #2
  10. ReAD: Reinforcement-Guided Capability Distillation for Large Language Models cs.CL · 2026 · author #4
  11. EpiGraph: Building Generalists for Evidence-Intensive Epilepsy Reasoning in the Wild cs.AI · 2026 · author #7
  12. LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis cs.AI · 2026 · author #3
  13. An Analysis of Active Learning Algorithms using Real-World Crowd-sourced Text Annotations cs.LG · 2026 · author #3
  14. From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges cs.CL · 2026 · author #6
  15. Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs cs.CR · 2025 · author #6
  16. ExPath: Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation cs.LG · 2025 · author #4
  17. Towards Certified Unlearning for Deep Neural Networks cs.LG · 2024 · author #2

Mentions

  • 2606.06906 #6 · arxiv_oai · confidence 0.70 Yushun Dong
  • 2606.06252 #6 · arxiv_oai · confidence 0.70 Yushun Dong
  • 2606.05725 #3 · arxiv_oai · confidence 0.70 Yushun Dong
  • 2512.04668 #6 · arxiv_oai · confidence 0.70 Yushun Dong
  • 2606.00232 #5 · arxiv_oai · confidence 0.70 Yushun Dong
  • 2605.30470 #4 · arxiv_oai · confidence 0.70 Yushun Dong
  • 2601.08654 #6 · arxiv_oai · confidence 0.70 Yushun Dong
  • 2605.12827 #5 · arxiv_oai · confidence 0.70 Yushun Dong
  • 2605.18911 #5 · arxiv_oai · confidence 0.70 Yushun Dong

Frequent Coauthors