The paper proposes DAMEL, a dual-axis multi-expert learning algorithm that simultaneously reduces both prediction bias and variance in class-imbalanced learning by leveraging multiple experts across b…

This paper diagnoses a bias-dominated shortcut in class-level machine unlearning, where forgetting is achieved by suppressing classification head biases, and proposes bias-aware mechanisms to mitigate…

BiasEdit introduces a training-free framework that automatically detects and edits unknown social biases in web-sourced image datasets to construct a debiased dataset for fair visual classification.

RogueMerge introduces a unified framework to robustly attack LLM model merging by addressing the challenges of autoregressive decoding, unknown merging configurations, and prompt generalization, signi…

The paper introduces a new anytime-valid inference method to correct split selection in online decision trees, providing robust statistical guarantees for streaming data that existing methods lack.

This paper identifies prediction bias, a failure mode of entropy minimization in test-time adaptation, and proposes Distribution Shift Bias Reduction (DSBR) to stabilize adaptation and prevent model c…

The paper introduces 5WBENCH, a new benchmark for causal unlearning, and proposes MAAT, a novel three-phase framework that achieves high forgetting and high retention specifically on complex 'Why'-typ…

CORE-MTL proposes a representation-centric framework that uses causal orthogonal representations to disentangle task-relevant structure from nuisance variation in multi-task learning, achieving superi…

The paper proposes FedSAP, a framework that stabilizes federated prototype learning by delaying global alignment and enforcing inter-class structure, significantly improving representation quality und…

The paper introduces Complexity-Balanced Splitting (CBS), a framework that efficiently allocates model capacity across the diffusion timeline by focusing computational resources on the most complex ge…

This paper develops a unified spectral analysis framework to explain how knowledge transfer (KT) works across different machine learning regimes, such as Knowledge Distillation and Weak-to-Strong gene…

The paper proposes a unified, constrained optimization framework using KL divergence and likelihood constraints to achieve effective and principled unlearning in diffusion models.

This paper compares traditional machine learning models (Random Forests, XGBoost, SVM) against a complex Unified Multi-Task Time Series Model for churn prediction, concluding that conventional methods…

This paper addresses the challenge of achieving optimal fairness and accuracy simultaneously in multi-class classification by proposing novel in-processing and post-processing algorithms that converge…

The paper proposes SubFit, a novel compression technique that achieves superior LLM compression by replacing non-contiguous, submodule-level components (Attention and FeedForward) with lightweight res…

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

This paper systematically investigates unlearnable examples (UEs) across diverse training paradigms, finding that existing UEs fail under pretraining-finetuning (PF) settings, and proposes Shallow Sem…

MARGIN proposes a margin-aware framework to detect software vulnerabilities by addressing geometric distortions caused by frequency and difficulty imbalances in embedding space, achieving superior per…