pith. sign in

Junhao Dong

Identifiers

  • name variant Junhao Dong 0.60 · backfill

Papers (16)

  1. Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction cs.AI · 2026 · author #5
  2. Adaptive Probe-based Steering for Robust LLM Jailbreaking cs.CR · 2026 · author #2
  3. A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook cs.SD · 2026 · author #25
  4. CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic cs.CV · 2026 · author #2
  5. ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition cs.CV · 2026 · author #3
  6. GaitProtector: Impersonation-Driven Gait De-Identification via Training-Free Diffusion Latent Optimization cs.CV · 2026 · author #4
  7. Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion cs.AI · 2026 · author #7
  8. EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs cs.CL · 2026 · author #12
  9. TSNN: A Non-parametric and Interpretable Framework for Traffic Time Series Forecasting cs.LG · 2026 · author #4
  10. BiAxisAudit: A Novel Framework to Evaluate LLM Bias Across Prompt Sensitivity and Response-Layer Divergence cs.CL · 2026 · author #2
  11. Hierarchically Robust Zero-shot Vision-language Models cs.CV · 2026 · author #1
  12. DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection cs.CV · 2026 · author #14
  13. Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks cs.LG · 2026 · author #3
  14. Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks cs.CL · 2025 · author #4
  15. Hard-Label Black-Box Attacks on 3D Point Clouds cs.CV · 2024 · author #3
  16. Discontinuous shear thickening of dense suspensions under confining pressure cond-mat.soft · 2017 · author #1

Mentions

  • 2606.01850 #5 · arxiv_oai · confidence 0.70 Junhao Dong
  • 2605.23954 #12 · arxiv_oai · confidence 0.70 Junhao Dong
  • 2602.00567 #3 · arxiv_oai · confidence 0.70 Junhao Dong
  • 2605.20286 #2 · arxiv_oai · confidence 0.70 Junhao Dong
  • 2605.20266 #25 · arxiv_oai · confidence 0.70 Junhao Dong
  • 2412.00404 #3 · arxiv_oai · confidence 0.70 Junhao Dong
  • 2605.18610 #2 · arxiv_oai · confidence 0.70 Junhao Dong
  • 2510.01782 #4 · arxiv_oai · confidence 0.70 Junhao Dong
  • 2605.14309 #3 · arxiv_oai · confidence 0.70 Junhao Dong

Frequent Coauthors