5 accepted papers
Multimodal generative models can process instructions in various modalities and demonstrate outstanding performance across a wide range of image generation tasks. However, their robustness in complex real-world scenarios remains limited due to insufficient generalized instruction alignment. We intro
Aligning diffusion models with human preferences remains challenging, particularly when reward models are unavailable or impractical to obtain, and collecting large-scale preference datasets is prohibitively expensive. This raises a fundamental question: can we achieve effective alignment using only…
Recent flow matching models for text-to-image generation have achieved remarkable quality, yet their integration with reinforcement learning for human preference alignment remains suboptimal, hindering fine-grained reward-based optimization. We observe that the key impediment to effective GRPO train…
Supervised fine-tuning (SFT) is widely adopted for tailoring large language models (LLMs) to specific downstream tasks. However, the substantial computational demands of LLMs hinder iterative exploration of fine-tuning datasets and accurate evaluation of individual sample importance. To address this…
Few-shot relation extraction (FSRE) has been a challenging problem since it only has a handful of training instances. Existing models follow a ‘one-for-all’ scheme where one general large model performs all individual N-way-K-shot tasks in FSRE, which prevents the model from achieving the optimal po…