Research map / Label-efficient and robust learning / Recognition and long-tail

U-MOF: Uncertainty-Guided Parameter-Efficient Multi-Objective Fine-Tuning for Long-Tailed Recognition

NeurIPS 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes U-MOF, an uncertainty-guided parameter-efficient multi-objective fine-tuning method for second-stage long-tailed recognition adaptation.

Problem

Second-stage fine-tuning for long-tailed recognition often allocates objective emphasis using delayed empirical summaries (historical class-wise performance or validation feedback) and restricts adaptation to a limited set of parameters.

Approach

Uses uncertainty to guide multi-objective emphasis during parameter-efficient second-stage fine-tuning, instead of delayed empirical summaries; the abstract indicates it goes beyond restricting adaptation to a narrow parameter subset.

Closest papers by meaning

• TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition (NeurIPS 2025 · similarity 0.96)
• Long-tailed Recognition with Model Rebalancing (NeurIPS 2025 · similarity 0.88)
• Decoupled Optimisation for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.87)
• Long-Tailed Learning as Multi-Objective Optimization (AAAI 2024 · similarity 0.87)
• Difficulty-aware Balancing Margin Loss for Long-tailed Recognition (AAAI 2025 · similarity 0.87)
• Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition (NeurIPS 2024 · similarity 0.87)