Related papers: Interpolating Strong Induction

Recently, prompt tuning methods for pre-trained models have demonstrated promising performance in Class Incremental Learning (CIL). These methods typically involve learning task-specific prompts and predicting the task ID to select the…

Deep learning has brought impressive progress in the study of both automatic speaker verification (ASV) and spoofing countermeasures (CM). Although solutions are mutually dependent, they have typically evolved as standalone sub-systems…

Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further…

Structure learning of Conditional Random Fields (CRFs) can be cast into an L1-regularized optimization problem. To avoid optimizing over a fully linked model, gain-based or gradient-based feature selection methods start from an empty model…

Intrusion Detection Systems (IDS) are now an essential element when it comes to securing computers and networks. Despite the huge research efforts done in the field, handling sources' reliability remains an open issue. To address this…

Deductive verification has been successful in verifying interesting properties of real-world programs. One notable gap is the limited support for floating-point reasoning. This is unfortunate, as floating-point arithmetic is particularly…

Reinforcement Learning from Verifiable Rewards (RLVR) has substantially enhanced the reasoning capabilities of large language models in abstract reasoning tasks. However, its application to Large Vision-Language Models (LVLMs) remains…

Autonomous driving vehicles (ADVs) are implemented with rich software functions and equipped with many sensors, which in turn brings broad attack surface. Moreover, the execution environment of ADVs is often open and complex. Hence, ADVs…

Deep neural network based question answering (QA) models are neither robust nor explainable in many cases. For example, a multiple-choice QA model, tested without any input of question, is surprisingly "capable" to predict the most of…

Calibrating deep learning models to yield uncertainty-aware predictions is crucial as deep neural networks get increasingly deployed in safety-critical applications. While existing post-hoc calibration methods achieve impressive results on…

Spoofing-robust automatic speaker verification (SASV) seeks to build automatic speaker verification systems that are robust against both zero-effort impostor attacks and sophisticated spoofing techniques such as voice conversion (VC) and…

Efficient key-value (KV) cache management is crucial for the practical deployment of large language models (LLMs), yet existing compression techniques often incur a trade-off between performance degradation and computational overhead. We…

In the realm of multimodal tasks, Visual Question Answering (VQA) plays a crucial role by addressing natural language questions grounded in visual content. Knowledge-Based Visual Question Answering (KBVQA) advances this concept by adding…

Leveraging well-established MCMC strategies, we propose MCMC-interactive variational inference (MIVI) to not only estimate the posterior in a time constrained manner, but also facilitate the design of MCMC transitions. Constructing a…

This paper improves the deep attractor network (DANet) approach by closing its gap between training and inference. During training, DANet relies on attractors, which are computed from the ground truth separations. As this information is not…

Recent deep learning (DL) models have moved beyond static network architectures to dynamic ones, handling data where the network structure changes every example, such as sequences of variable lengths, trees, and graphs. Existing…

Because it determines a center-outward ordering of observations in $\mathbb{R}^d$ with $d\geq 2$, the concept of statistical depth permits to define quantiles and ranks for multivariate data and use them for various statistical tasks (e.g.…

In this work, we develop a computational method that to provide realtime detection for water bottom topography based on observations on surface measurements, and we design an inverse problem to achieve this task. The forward model that we…

The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache. Existing eviction or compression methods reduce cost but rely on…

We present a new deep meta reinforcement learner, which we call Deep Episodic Value Iteration (DEVI). DEVI uses a deep neural network to learn a similarity metric for a non-parametric model-based reinforcement learning algorithm. Our model…