相关论文: Visual Instruction Tuning with Polite Flamingo

Fine-tuning large language models (LLMs) on multi-task instruction-following data has been proven to be a powerful learning paradigm for improving their zero-shot capabilities on new tasks. Recent works about high-quality…

Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision…

Bootstrapping from pre-trained language models has been proven to be an efficient approach for building vision-language models (VLM) for tasks such as image captioning or visual question answering. However, outputs of these models rarely…

Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models (LLMs) with human-annotated demonstrations. However, SFT, being an off-policy approach similar to behavior cloning, often struggles with…

Large Language Models (LLMs) have transformed natural language processing, but concerns have emerged about their susceptibility to ideological manipulation, particularly in politically sensitive areas. Prior work has focused on binary…

Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve…

Pre-trained language models (PLM) have revolutionized the NLP landscape, achieving stellar performances across diverse tasks. These models, while benefiting from vast training data, often require fine-tuning on specific data to cater to…

In this paper, we introduce ILLUME, a unified multimodal large language model (MLLM) that seamlessly integrates multimodal understanding and generation capabilities within a single large language model through a unified next-token…

Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tasks such as object counting or spatial reasoning. We…

Multimodal large language models are typically trained in two stages: first pre-training on image-text pairs, and then fine-tuning using supervised vision-language instruction data. Recent studies have shown that large language models can…

Active learning aims to reduce annotation cost by selectively querying informative samples for supervision under a limited labeling budget. In this work, we investigate how vision-language models (VLMs) can be leveraged to further reduce…

Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision-language models (VLMs). While RL-tuned VLMs improve on visual…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving…

Mainstream approaches to aligning large language models (LLMs) heavily rely on human preference data, particularly when models require periodic updates. The standard process for iterative alignment of LLMs involves collecting new human…

Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a…

Instruction tuning -- supervised fine-tuning using instruction-response pairs -- is a key step in making pre-trained large language models (LLMs) instructable. Meanwhile, LLMs perform multitask learning during their pre-training, acquiring…

Multi-modal Large Language Models (MLLMs) are increasingly prominent in the field of artificial intelligence. Visual instruction fine-tuning (IFT) is a vital process for aligning MLLMs' output with user's intentions. High-quality and…

Pre-trained Language Models (PLMs) have achieved remarkable performance for various language understanding tasks in IR systems, which require the fine-tuning process based on labeled training data. For low-resource scenarios, prompt-based…

Large language models (LLMs) have demonstrated remarkable capabilities in various tasks. However, their suitability for domain-specific tasks, is limited due to their immense scale at deployment, susceptibility to misinformation, and more…