Related papers: APEX: Learning Adaptive Priorities for Multi-Objec…

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model…

The automatic classification of occupational accident reports is pivotal for workplace safety analysis but is persistently hindered by severe class imbalance and data scarcity. In this paper, we propose ABEX-RAT, a resource-efficient…

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Diffusion models generate highly realistic images but often struggle with precise text-image alignment. While recent post-training methods improve alignment using external rewards or human preference signals, their performance heavily…

Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward models remains a significant challenge. Existing multi-reward fusion approaches rely on…

Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models. The issue is exacerbated when the task involves complex structured outputs, as it becomes harder to design procedures…

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with…

How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class similarity, whether by constructing positive and negative…

Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimensions remains a persistent challenge. Though reinforcement…

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models. However, due to the lack of focus in feedback content, especially regarding the object type and quantity,…

Autoregressive next-token training offers a unified formulation for image generation and text understanding, but it also creates strong modality competition that destabilizes optimization and limits large-batch scaling. We show that…

Reward modeling is essential for aligning large language models with human preferences, yet predominant architectures rely on a static pooling strategy to condense sequences into scalar scores. This paradigm, however, suffers from two key…

Recent studies have demonstrated the effectiveness of directly aligning diffusion models with human preferences using differentiable reward. However, they exhibit two primary challenges: (1) they rely on multistep denoising with gradient…

In this paper, we introduce a framework ARBEx, a novel attentive feature extraction framework driven by Vision Transformer with reliability balancing to cope against poor class distributions, bias, and uncertainty in the facial expression…

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

Real-world problems are often multi-objective with decision-makers unable to specify a priori which trade-off between the conflicting objectives is preferable. Intuitively, building machine learning solutions in such cases would entail…

High-quality training triplets (instruction, original image, edited image) are essential for instruction-based image editing. Predominant training datasets (e.g., InsPix2Pix) are created using text-to-image generative models (e.g., Stable…

Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context…

Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual shifts pose practical challenges. A key difficulty is that standard task rewards supervise…