Related papers: Text-driven 3D Human Generation via Contrastive Pr…

Alignment with human preferences is commonly framed using a universal reward function, even though human preferences are inherently heterogeneous. We formalize this heterogeneity by introducing user types and examine the limits of the…

By leveraging the text-to-image diffusion priors, score distillation can synthesize 3D contents without paired text-3D training data. Instead of spending hours of online optimization per text prompt, recent studies have been focused on…

User modeling, which aims to capture users' characteristics or interests, heavily relies on task-specific labeled data and suffers from the data sparsity issue. Several recent studies tackled this problem by pre-training the user model on…

Aligning large language models (LLMs) with human preferences is crucial for safe deployment, yet existing methods assume specific preference models like Bradley-Terry model. This assumption leads to statistical inconsistency, where more…

As language models (LMs) become more capable, it is increasingly important to align them with human preferences. However, the dominant paradigm for training Preference Models (PMs) for that purpose suffers from fundamental limitations, such…

Learning from preference feedback is essential for aligning large language models (LLMs) with human values and improving the quality of generated responses. However, existing preference learning methods rely heavily on curated data from…

Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being supervised, SFT is inherently limited by its generative…

Text-guided image and 3D editing have advanced with diffusion-based models, yet methods like Delta Denoising Score often struggle with stability, spatial control, and editing strength. These limitations stem from reliance on complex…

Recently, large multimodal models, such as CLIP and Stable Diffusion have experimented tremendous successes in both foundations and applications. However, as these models increase in parameter size and computational requirements, it becomes…

Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models (LLMs) with human preferences, thereby enhancing the quality of responses generated. A critical component of RLHF is the reward model,…

As text generative models can give increasingly long answers, we tackle the problem of synthesizing long text in digital ink. We show that the commonly used models for this task fail to generalize to long-form data and how this problem can…

Modern machine learning models for scene understanding, such as depth estimation and object tracking, rely on large, high-quality datasets that mimic real-world deployment scenarios. To address data scarcity, we propose an end-to-end system…

Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting these priors to complex visual modalities, often represented…

Though offering amazing contextualized token-level representations, current pre-trained language models actually take less attention on acquiring sentence-level representation during its self-supervised pre-training. If self-supervised…

Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with…

In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks. Our method, called…

Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets into significantly smaller yet informative synthetic datasets.…

The field of text-to-3D content generation has made significant progress in generating realistic 3D objects, with existing methodologies like Score Distillation Sampling (SDS) offering promising guidance. However, these methods often…

We present a method for improving human design of chairs. The goal of the method is generating enormous chair candidates in order to facilitate human designer by creating sketches and 3d models accordingly based on the generated chair…

Contrastive learning has been successfully used for retrieval of semantically aligned sentences, but it often requires large batch sizes or careful engineering to work well. In this paper, we instead propose a generative model for learning…