Related papers: Diversify, Contextualize, and Adapt: Efficient Ent…

An agent in a nonstationary contextual bandit problem should balance between exploration and the exploitation of (periodic or structured) patterns present in its previous experiences. Handcrafting an appropriate historical context is an…

In neural video codecs, current state-of-the-art methods typically adopt multi-scale motion compensation to handle diverse motions. These methods estimate and compress either optical flow or deformable offsets to reduce inter-frame…

Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…

Contextual policy search allows adapting robotic movement primitives to different situations. For instance, a locomotion primitive might be adapted to different terrain inclinations or desired walking speeds. Such an adaptation is often…

Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression…

Diffusion models achieve state-of-the-art generative performance but suffer from high computational costs during inference due to the repeated evaluation of a heavy neural network. In this work, we propose Dual-Rate Diffusion, a method to…

As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many…

This paper proposes an adaptive neural-compilation framework to address the problem of efficient program learning. Traditional code optimisation strategies used in compilers are based on applying pre-specified set of transformations that…

The ability to quickly learn new knowledge (e.g. new classes or data distributions) is a big step towards human-level intelligence. In this paper, we consider scenarios that require learning new classes or data distributions quickly and…

To enhance image compression performance, recent deep neural network-based research can be divided into three categories: a learnable codec, a postprocessing network, and a compact representation network. The learnable codec has been…

In recent years, neural image compression (NIC) algorithms have shown powerful coding performance. However, most of them are not adaptive to the image content. Although several content adaptive methods have been proposed by updating the…

In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network. A challenging problem as such results in unwelcome complexity increase and inferior…

Image codecs are typically optimized to trade-off bitrate \vs distortion metrics. At low bitrates, this leads to compression artefacts which are easily perceptible, even when training with perceptual or adversarial losses. To improve image…

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…

Finding better solutions to combinatorial optimization problems could have a large positive impact on many real-world application areas, such as logistics. For this reason, significant efforts have been made to design novel optimisation…

Learned image compression (LIC) methods have recently outperformed traditional codecs such as VVC in rate-distortion performance. However, their large models and high computational costs have limited their practical adoption. In this paper,…

Explicit feature-grid based NeRF models have shown promising results in terms of rendering quality and significant speed-up in training. However, these methods often require a significant amount of data to represent a single scene or…

Biological visual systems learn from limited experience, unlike deep learning models that rely on millions of training images. What learning principles make this possible? We tested whether efficient coding, the idea that neural…

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…

High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments. To handle high-dimensional sensory inputs, existing approaches use representation learning to…