Tag: Foundation Model
All the articles with the tag "Foundation Model".
-
Contextures: Representations from Contexts
This paper introduces the contexture theory, unifying representation learning across paradigms by targeting top singular functions of a context-induced expectation operator, demonstrating high alignment in neural representations and proposing a task-agnostic metric for context evaluation with strong empirical correlation to performance on various datasets.
-
Kimi-Audio Technical Report
本文提出Kimi-Audio,一个开源的音频基础模型,通过结合音频分词、LLM处理和逆分词的统一架构,以及大规模多模态训练,实现了音频理解、生成和对话的多任务SOTA性能。
-
ULFine: Unbiased Lightweight Fine-tuning for Foundation-Model-Assisted Long-Tailed Semi-Supervised Learning
This paper introduces ULFine, an unbiased lightweight fine-tuning strategy for foundation-model-assisted long-tailed semi-supervised learning, which mitigates 'minority bottleneck' and 'majority overconfidence' issues using Prototype Adaptive Fitting and Dual Logit Fusion, achieving significant performance improvements and over 10x training cost reduction on benchmark datasets.