The Neglected Tails in Vision-Language Models
Vision-language models (VLMs) excel in zero-shot recognition but their performance varies
greatly across different visual concepts. For example although CLIP achieves impressive …
greatly across different visual concepts. For example although CLIP achieves impressive …
On catastrophic inheritance of large foundation models
Large foundation models (LFMs) are claiming incredible performances. Yet great concerns
have been raised about their mythic and uninterpreted potentials not only in machine …
have been raised about their mythic and uninterpreted potentials not only in machine …
Selective Vision-Language Subspace Projection for Few-shot CLIP
Vision-language models such as CLIP are capable of mapping the different modality data
into a unified feature space, enabling zero/few-shot inference by measuring the similarity of …
into a unified feature space, enabling zero/few-shot inference by measuring the similarity of …
Generalization Beyond Data Imbalance: A Controlled Study on CLIP for Transferable Insights
Severe data imbalance naturally exists among web-scale vision-language datasets. Despite
this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance …
this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance …
Bias-Aware Low-Rank Adaptation: Mitigating Catastrophic Inheritance of Large Language Models
Large language models (LLMs) have exhibited remarkable proficiency across a diverse
array of natural language processing (NLP) tasks. However, adapting LLMs to downstream …
array of natural language processing (NLP) tasks. However, adapting LLMs to downstream …