Related papers: GIFT: Guided Importance-Aware Fine-Tuning for Diff…

Diffusion models have emerged as a promising approach for text generation, with recent works falling into two main categories: discrete and continuous diffusion models. Discrete diffusion models apply token corruption independently using…

Internal features from large-scale pre-trained diffusion models have recently been established as powerful semantic descriptors for a wide range of downstream tasks. Works that use these features generally need to add noise to images before…

By pretraining on trillions of tokens, an LLM gains the capability of text generation. However, to enhance its utility and reduce potential harm, SFT and alignment are applied sequentially to the pretrained model. Because SFT and alignment…

Diffusion models are highly regarded for their controllability and the diversity of images they generate. However, class-conditional generation methods based on diffusion models often focus on more common categories. In large-scale…

Widely used language models (LMs) are typically built by scaling up a two-stage training pipeline: a pre-training stage that uses a very large, diverse dataset of text and a fine-tuning (sometimes, 'alignment') stage that uses targeted…

Supervised fine-tuning (SFT) plays a crucial role in adapting large language models (LLMs) to specific domains or tasks. However, as demonstrated by empirical experiments, the collected data inevitably contains noise in practical…

Low-Rank Adaptation (LoRA) and other parameter-efficient fine-tuning (PEFT) methods provide low-memory, storage-efficient solutions for personalizing text-to-image models. However, these methods offer little to no improvement in wall-clock…

Recent advances in large-scale generative language models have shown that reasoning capabilities can significantly improve model performance across a variety of tasks. However, the impact of reasoning on a model's ability to mitigate…

Recently, diffusion models have garnered significant interest in the field of text processing due to their many potential advantages compared to conventional autoregressive models. In this work, we propose Diffusion-of-Thought (DoT), a…

Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution…

While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert data or discard valuable negative samples, leading to data inefficiency. To address this, we…

While large language models (LLMs) are increasingly adapted for recommendation systems via supervised fine-tuning (SFT), this approach amplifies popularity bias due to its likelihood maximization objective, compromising recommendation…

Large language models (LLMs) have demonstrated significant improvements in contextual understanding. However, their ability to attend to truly critical information during long-context reasoning and generation still falls behind the pace.…

Facial attribute editing and style manipulation are crucial for applications like virtual avatars and photo editing. However, achieving precise control over facial attributes without altering unrelated features is challenging due to the…

Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive…

Parameter-efficient fine-tuning (PEFT) has become a common method for fine-tuning large language models, where a base model can serve multiple users through PEFT module switching. To enhance user experience, base models require periodic…

Finetuning language models for a new domain inevitably leads to the deterioration of their general performance. This becomes more pronounced the more limited the finetuning data resource. We introduce minifinetuning (MFT), a method for…

Multimodal large language models (MLLMs) have made rapid progress, yet their reasoning ability often lags behind strong text-only LLMs. Bridging this gap typically requires large-scale multimodal reasoning data or reinforcement learning,…

Large language models (LLMs) have achieved remarkable success across various tasks but face deployment challenges due to their massive computational demands. While post-training pruning methods like SparseGPT and Wanda can effectively…

Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual…