Related papers: Jointly Optimizing Diversity and Relevance in Neur…

We present a joint modeling approach to identify salient discussion points in spoken meetings as well as to label the discourse relations between speaker turns. A variation of our model is also discussed when discourse relations are treated…

We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. While previous fusion methods use an explicit scene representation like signed distance functions (SDFs), we propose a learned…

For the last decade, there has been a push to use multi-dimensional (latent) spaces to represent concepts; and yet how to manipulate these concepts or reason with them remains largely unclear. Some recent methods exploit multiple latent…

Medical time series are often irregular and face significant missingness, posing challenges for data analysis and clinical decision-making. Existing methods typically adopt a single modeling perspective, either treating series data as…

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…

Natural human interactions for Mixed Reality Applications are overwhelmingly multimodal: humans communicate intent and instructions via a combination of visual, aural and gestural cues. However, supporting low-latency and accurate…

Language models have demonstrated remarkable capabilities on standard benchmarks, yet they struggle increasingly from mode collapse, the inability to generate diverse and novel outputs. Our work introduces NoveltyBench, a benchmark…

Sequential recommendation models have achieved state-of-the-art performance using self-attention mechanism. It has since been found that moving beyond only using item ID and positional embeddings leads to a significant accuracy boost when…

3D occupancy prediction based on multi-sensor fusion,crucial for a reliable autonomous driving system, enables fine-grained understanding of 3D scenes. Previous fusion-based 3D occupancy predictions relied on depth estimation for processing…

Despite the recent advances in open-domain dialogue systems, building a reliable evaluation metric is still a challenging problem. Recent studies proposed learnable metrics based on classification models trained to distinguish the correct…

Reward modeling, crucial for aligning large language models (LLMs) with human preferences, is often bottlenecked by the high cost of preference data. Existing textual data synthesis methods are computationally expensive. We propose a novel…

The size of training dataset is known to be among the most dominating aspects of training high-performance face recognition embedding model. Building a large dataset from scratch could be cumbersome and time-intensive, while combining…

We present StyleFusion, a new mapping architecture for StyleGAN, which takes as input a number of latent codes and fuses them into a single style code. Inserting the resulting style code into a pre-trained StyleGAN generator results in a…

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by…

In human conversation an input post is open to multiple potential responses, which is typically regarded as a one-to-many problem. Promising approaches mainly incorporate multiple latent mechanisms to build the one-to-many relationship.…

We address the problem of tuning word embeddings for specific use cases and domains. We propose a new method that automatically combines multiple domain-specific embeddings, selected from a wide range of pre-trained domain-specific…

Providing recommendations that are both relevant and diverse is a key consideration of modern recommender systems. Optimizing both of these measures presents a fundamental trade-off, as higher diversity typically comes at the cost of…

Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion alignment. Some align text and motion latent spaces but sacrifice expressiveness;…

The sequence-to-sequence (Seq2Seq) model generates target words iteratively given the previously observed words during decoding process, which results in the loss of the holistic semantics in the target response and the complete semantic…

Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models. Despite its advantageous properties, prior methods…