Related papers: SODA: Semantic-Oriented Distributional Alignment f…

Slot Attention (SA) with pretrained diffusion models has recently shown promise for object-centric learning (OCL), but suffers from slot entanglement and weak alignment between object slots and image content. We propose Contrastive…

Data scarcity has been a long standing issue in the field of open-domain social dialogue. To quench this thirst, we present SODA: the first publicly available, million-scale high-quality social dialogue dataset. By contextualizing social…

Generative design refers to computational design methods that can automatically conduct design exploration under constraints defined by designers. Among many approaches, topology optimization-based generative designs aim to explore diverse…

With the prevalence of social networks on online platforms, social recommendation has become a vital technique for enhancing personalized recommendations. The effectiveness of social recommendations largely relies on the social homophily…

Although sequence-to-sequence models often achieve good performance in semantic parsing for i.i.d. data, their performance is still inferior in compositional generalization. Several data augmentation methods have been proposed to alleviate…

Recent advancements in large language model alignment leverage token-level supervisions to perform fine-grained preference optimization. However, existing token-level alignment methods either optimize on all available tokens, which can be…

We study zeroth-order optimization where solutions must minimize a cost $d(s)$ while maintaining high probability under a complex generative prior $L(s)$ (e.g., a parameterized model). This reduces to sampling from a target distribution…

Traditional recommendation models often rely on unique item identifiers (IDs) to distinguish between items, which can hinder their ability to effectively leverage item content information and generalize to long-tailed or cold-start items.…

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…

This work proposes a simple yet effective sampling framework for combinatorial optimization (CO). Our method builds on discrete Langevin dynamics (LD), an efficient gradient-guided generative paradigm. However, we observe that directly…

E-commerce recommendation systems aim to generate ordered lists of items for customers, optimizing multiple business objectives, such as clicks, conversions and Gross Merchandise Volume (GMV). Traditional multi-objective optimization…

Distribution regression refers to the supervised learning problem where labels are only available for groups of inputs instead of individual inputs. In this paper, we develop a rigorous mathematical framework for distribution regression…

The growth of domain-specific applications of semantic models, boosted by the recent achievements of unsupervised embedding learning algorithms, demands domain-specific evaluation datasets. In many cases, content-based recommenders being a…

Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application. However, the traditional adaptation by further training on in-domain data rapidly weakens the model's ability to…

Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. Unfortunately, a simple combination of domain…

Recent studies have addressed the concern of detecting and rejecting the out-of-distribution (OOD) samples as a major challenge in the safe deployment of deep learning (DL) models. It is desired that the DL model should only be confident…

In programming, learning code representations has a variety of applications, including code classification, code search, comment generation, bug prediction, and so on. Various representations of code in terms of tokens, syntax trees,…

Supervised Semantic Differential (SSD) is a mixed quantitative-interpretive method that models how text meaning varies with continuous individual-difference variables by estimating a semantic gradient in an embedding space and interpreting…

Personalization plays an important role in many services. To evaluate personalized rankings, online evaluation, such as A/B testing, is widely used today. Recently, multileaving has been found to be an efficient method for evaluating…

Generative recommendation reformulates recommendation as next-token prediction over discrete semantic identifiers (IDs). A fundamental yet unexplored design choice is that existing methods employ fixed-length tokenization for all items,…