Related papers: Instruction-aware User Embedding via Synergistic L…
Representation learning, a task of learning latent vectors to represent entities, is a key task in improving search and recommender systems in web applications. Various representation learning methods have been developed, including…
Universal multimodal embedding models play a critical role in tasks such as interleaved image-text retrieval, multimodal RAG, and multimodal clustering. However, our empirical results indicate that existing LMM-based embedding models…
Intent-based recommender systems have garnered significant attention for uncovering latent fine-grained preferences. Intents, as underlying factors of interactions, are crucial for improving recommendation interpretability. Most methods…
Decoder-only large language models are increasingly used as behavioral encoders for user representation learning, yet the impact of attention masking on the quality of user embeddings remains underexplored. In this work, we conduct a…
Instruction-following is a foundational capability of large language models (LLMs), with its improvement hinging on scalable and accurate feedback from judge models. However, the reliability of current judge models in instruction-following…
With instruction tuning, Large Language Models (LLMs) can enhance their ability to adhere to commands. Diverging from most works focusing on data mixing, our study concentrates on enhancing the model's capabilities from the perspective of…
Humans can collaborate and complete tasks based on visual signals and instruction from the environment. Training such a robot is difficult especially due to the understanding of the instruction and the complicated environment. Previous…
Navigating certain communication situations can be challenging due to individuals' lack of skills and the interference of strong emotions. However, effective learning opportunities are rarely accessible. In this work, we conduct a…
We present a novel framework for user representation in large-scale recommender systems, aiming at effectively representing diverse user taste in a generalized manner. Our approach employs a two-stage methodology combining representation…
Large Language Models (LLMs) have the potential to transform the way a dynamic curriculum can be delivered. However, educators face significant challenges in interacting with these models, particularly due to complex prompt engineering and…
An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations. However, due to the large…
The rapid advancement of Large Multi-modal Foundation Models (LMM) has paved the way for the possible Explainable Image Quality Assessment (EIQA) with instruction tuning from two perspectives: overall quality explanation, and attribute-wise…
Decoder-only LLM-based embedding models are beginning to outperform BERT or T5-based embedding models in general-purpose text embedding tasks, including dense vector-based retrieval. In this work, we introduce NV-Embed, incorporating…
Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…
Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…
Large Language Models (LLMs) have demonstrated remarkable efficacy in text embedding, yet current adaptation methods like LoRA face significant bottlenecks in computational efficiency and cross-architecture transferability. Whenever a new…
Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient…
Perceptual learning enables humans to recognize and represent stimuli invariant to various transformations and build a consistent representation of the self and physical world. Such representations preserve the invariant physical relations…
We propose Context-Adaptive Multi-Prompt Embedding, a novel approach to enrich semantic representations in vision-language contrastive learning. Unlike standard CLIP-style models that rely on a single text embedding, our method introduces…
Aligning large language models (LLMs) with human expectations requires high-quality instructional dialogues, which usually require instructions that are diverse and in-depth. Existing methods leverage two LLMs to interact for automatic…