HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning

Documenti analoghi

• Rank-O-ToM: Unlocking Emotional Nuance Ranking to Enhance Affective Theory-of-Mind
  di: Kim, JiHyun, et al.
  Pubblicazione: (2025)
• Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias
  di: Kwon, JuneHyoung, et al.
  Pubblicazione: (2026)
• See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
  di: Kwon, JuneHyoung, et al.
  Pubblicazione: (2025)
• Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks
  di: Kwon, JuneHyoung, et al.
  Pubblicazione: (2026)
• Position on LLM-Assisted Peer Review: Addressing Reviewer Gap through Mentoring and Feedback
  di: Yun, JungMin, et al.
  Pubblicazione: (2026)