Real-world data universally confronts a severe class-imbalance problem and exhibits a long-tailed distribution, i.e., most labels are associated with limited instances. The naïve models supervised by such datasets would prefer dominant labels, encounter a serious generalization challenge and become poorly calibrated. We propose two novel methods from the prior perspective to alleviate this dilemma. First, we deduce a balance-oriented data augmentation named Uniform Mixup (UniMix) to promote mixup in long-tailed scenarios, which adopts advanced mixing factor and sampler in favor of the minority. Second, motivated by the Bayesian theory, we figure out the Bayes Bias (Bayias), an inherent bias caused by the inconsistency of prior, and compensate it as a modification on standard cross-entropy loss. We further prove that both the proposed methods ensure the classification calibration theoretically and empirically. Extensive experiments verify that our strategies contribute to a better-calibrated model and their combination achieves state-of-the-art performance on CIFAR-LT, ImageNet-LT, and iNaturalist 2018.

However, mostsamplesarestill -Augfortheheadormiddle (see Fig.2(green)). Hence, (x; coulduselikelihoodP(X = x|Y = y) oftrain P(Y =y|X =x)intestset.Ptrain(Y =yi)= yi andPt yi) 1/C,priorcannotbe prior, thelearned , W, b, willyield isnolongerpriorshould correctness By = log y) + logC) Furthermore, By enables likelihood, TheoremBy-compensated LB(yi, (x; )) = l h 1+ X E2E: end : ourreproduced : results Dataset ImageNet-LiNaturalist Method E2EResNet-10 ResNet-50 ResNet-50 CE 3 35.88

Long-context processing is a critical ability that constrains the applicability of large language models. Although there exist various methods devoted to enhancing the long-context processing ability of large language models (LLMs), they are developed in an isolated manner and lack systematic analysis and integration of their strengths, hindering further developments. In this paper, we introduce UniMem, a unified framework that reformulates existing long-context methods from the view of memory augmentation of LLMs. UniMem is characterized by four key dimensions: Memory Management, Memory Writing, Memory Reading, and Memory Injection, providing a systematic theory for understanding various long-context methods. We reformulate 16 existing methods based on UniMem and analyze four representative methods: Transformer-XL, Memorizing Transformer, RMT, and Longformer into equivalent UniMem forms to reveal their design principles and strengths. Based on these analyses, we propose UniMix, an innovative approach that integrates the strengths of these algorithms. Experimental results show that UniMix achieves superior performance in handling long contexts with significantly lower perplexity than baselines.