pith. sign in

Longtao Huang

Identifiers

  • name variant Longtao Huang 0.60 · backfill

Papers (13)

  1. ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails cs.CL · 2026 · author #9
  2. How LoRA Remembers? A Parametric Memory Law for LLM Finetuning cs.CL · 2026 · author #5
  3. Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers cs.AI · 2026 · author #8
  4. Make LLM Learn to Synthesize from Streaming Experiences through Feedback cs.AI · 2026 · author #6
  5. The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works cs.LG · 2026 · author #6
  6. Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack cs.LG · 2026 · author #5
  7. FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence cs.CV · 2026 · author #12
  8. simpleposter: a simple baseline for product poster generation cs.CV · 2026 · author #6
  9. XekRung Technical Report cs.CR · 2026 · author #8
  10. Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts cs.CV · 2026 · author #6
  11. How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities cs.CL · 2026 · author #5
  12. Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics cs.CL · 2026 · author #7
  13. Automated Strabismus Detection for Telemedicine Applications cs.CV · 2018 · author #5

Mentions

  • 2605.31073 #9 · arxiv_oai · confidence 0.70 Longtao Huang
  • 2605.30260 #5 · arxiv_oai · confidence 0.70 Longtao Huang
  • 2605.30049 #8 · arxiv_oai · confidence 0.70 Longtao Huang
  • 2605.29940 #6 · arxiv_oai · confidence 0.70 Longtao Huang
  • 2605.26246 #6 · arxiv_oai · confidence 0.70 Longtao Huang
  • 2605.25194 #5 · arxiv_oai · confidence 0.70 Longtao Huang

Frequent Coauthors