5 papers
DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks
Wei Cui, Tongzi Wu, Jesse C. Cresswell +2
Meta-learning represents a strong class of approaches for solving few-shot learning tasks. Nonetheless, recent research suggests that simply pre-training a generic encoder can pote…
RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator
Zhenwei Tang, Zhaoyan Liu, Rasa Hosseinzadeh +3
As interactive LLM-based applications are created and refined, model developers need to evaluate the quality of generated text along many possible axes. For simpler systems, human…
EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling
Jiafei Song, Fengwei Zhou, Jin Qu +7
Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the…
Self-Supervised Representation Learning as Mutual Information Maximization
Akhlaqur Rahman Sabby, Yi Sui, Tongzi Wu +2
Self-supervised representation learning (SSRL) has demonstrated remarkable empirical success, yet its underlying principles remain insufficiently understood. While recent works att…
A Geometric Framework for Understanding Memorization in Generative Models
Brendan Leigh Ross, Hamidreza Kamkari, Tongzi Wu +5
As deep generative models have progressed, recent work has shown them to be capable of memorizing and reproducing training datapoints when deployed. These findings call into questi…