Related papers: Break-for-Make: Modular Low-Rank Adaptations for C…

Recently, efficient fine-tuning of large-scale pre-trained models has attracted increasing research interests, where linear probing (LP) as a fundamental module is involved in exploiting the final representations for task-dependent…

Personalized text-to-image generation aims to synthesize images of user-provided concepts in diverse contexts. Despite recent progress in multi-concept personalization, most are limited to object concepts and struggle to customize abstract…

Adaptive learning aims to stimulate and meet the needs of individual learners, which requires sophisticated system-level coordination of diverse tasks, including modeling learning resources, estimating student states, and making…

Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the problem into two…

Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making content moderation an indispensable task. A common approach…

Curriculum learning is a widely adopted training strategy in natural language processing (NLP), where models are exposed to examples organized by increasing difficulty to enhance learning efficiency and performance. However, most existing…

Foundation models are increasingly used to personalize learning, yet many systems still assume fixed curricula or coarse progress signals, limiting alignment with learners' day-to-day needs. At the other extreme, lightweight incidental…

Low-rank adapters enable fine-tuning of large models with only a small number of parameters, thus reducing storage costs and minimizing the risk of catastrophic forgetting. However, they often pose optimization challenges, with poor…

Large pretrained language models (PLMs) are often domain- or task-adapted via fine-tuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and…

For a long time, different recommendation tasks typically require designing task-specific architectures and training objectives. As a result, it is hard to transfer the learned knowledge and representations from one task to another, thus…

Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are…

Designing visually diverse and high-quality designs remains a manual, time-consuming process, limiting scalability and personalization in creative workflows. We present a system for generating editable design variations using a decoder-only…

The personalization of black-box large language models (LLMs) is a critical yet challenging task. Existing approaches predominantly rely on context injection, where user history is embedded into the prompt to directly guide the generation…

We present a system for bottom-up cumulative learning of myriad concepts corresponding to meaningful character strings, and their part-related and prediction edges. The learning is self-supervised in that the concepts discovered are used as…

Contrastive vision-language models, such as CLIP, have garnered considerable attention for various downstream tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often…

Recognizing and generating object-state compositions has been a challenging task, especially when generalizing to unseen compositions. In this paper, we study the task of cutting objects in different styles and the resulting object state…

Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities. However, controlling attributes of the generated language (e.g. switching topic or sentiment) is difficult without…

With the rapid scaling of large language models (LLMs), serving numerous low-rank adaptations (LoRAs) concurrently has become increasingly impractical, leading to unaffordable costs and necessitating more parameter-efficient finetuning…

Contrastive vision-language models (e.g. CLIP) are typically created by updating all the parameters of a vision model and language model through contrastive training. Can such models be created by a small number of parameter updates to an…

Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-training on massive domain-specific corpora to facilitate…