Related papers: Dynamic Oracles for Top-Down and In-Order Shift-Re…

In this work, we propose a progressive scaling training strategy for visual object tracking, systematically analyzing the influence of training data volume, model size, and input resolution on tracking performance. Our empirical study…

State-of-the-art speaker verification frameworks have typically focused on developing models with increasingly deeper (more layers) and wider (number of channels) models to improve their verification performance. Instead, this paper…

Token-level adaptive computation seeks to reduce inference cost by allocating more computation to harder tokens and less to easier ones. However, prior work is primarily evaluated on natural-language benchmarks using task-level metrics,…

A consequent approach is proposed to construct symplectic force-gradient algorithms of arbitrarily high orders in the time step for precise integration of motion in classical and quantum mechanics simulations. Within this approach the basic…

Multi-head self-attention forms the core of Transformer networks. However, their quadratically growing complexity with respect to the input sequence length impedes their deployment on resource-constrained edge devices. We address this…

Designing off-policy reinforcement learning algorithms is typically a very challenging task, because a desirable iteration update often involves an expectation over an on-policy distribution. Prior off-policy actor-critic (AC) algorithms…

It has long been hoped that model-based control will improve tracking performance while maintaining or increasing compliance. This hope hinges on having or being able to estimate an accurate inverse dynamics model. As a result, substantial…

Due to its great importance in deep natural language understanding and various down-stream applications, text-level parsing of discourse rhetorical structure (DRS) has been drawing more and more attention in recent years. However, all the…

A number of differences have emerged between modern and classic approaches to constituency parsing in recent years, with structural components like grammars and feature-rich lexicons becoming less central while recurrent neural network…

Diffusion policies trained via offline behavioral cloning have recently gained traction in robotic motion generation. While effective, these policies typically require a large number of trainable parameters. This model size affords powerful…

We propose a projection-free conditional gradient-type algorithm for smooth stochastic multi-level composition optimization, where the objective function is a nested composition of $T$ functions and the constraint set is a closed convex…

Conformer-based end-to-end models have become ubiquitous these days and are commonly used in both streaming and non-streaming automatic speech recognition (ASR). Techniques like dual-mode and dynamic chunk training helped unify streaming…

The automation of extracting argument structures faces a pair of challenges on (1) encoding long-term contexts to facilitate comprehensive understanding, and (2) improving data efficiency since constructing high-quality argument structures…

We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR. This new formulation directly uses box coordinates as queries in…

Reinforcement learning (RL) in large or infinite state spaces is notoriously challenging, both theoretically (where worst-case sample and computational complexities must scale with state space cardinality) and experimentally (where function…

The Transformer architecture is widely used for machine translation tasks. However, its resource-intensive nature makes it challenging to implement on constrained embedded devices, particularly where available hardware resources can vary at…

We present OptiReduce, a new collective-communication system for the cloud with bounded, predictable completion times for deep-learning jobs in the presence of varying computation (stragglers) and communication (congestion and gradient…

Robust optimization (RO) has emerged as one of the leading paradigms to efficiently model parameter uncertainty. The recent connections between RO and problems in statistics and machine learning domains demand for solving RO problems in…

Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a policy is trained to maximize a learned value function while…

Syntax is fundamental to our thinking about language. Failing to capture the structure of input language could lead to generalization problems and over-parametrization. In the present work, we propose a new syntax-aware language model:…