Related papers: Tag-Evol: Achieving Efficient Instruction Evolving…

The exponential growth of volume, variety and velocity of data is raising the need for investigations of automated or semi-automated ways to extract useful patterns from the data. It requires deep expert knowledge and extensive…

Vision--Language--Action (VLA) policies have shown strong progress in mapping language instructions and visual observations to robotic actions, yet their reliability degrades in cluttered scenes with distractors. By analyzing failure cases,…

Neuroevolution is one of the methodologies that can be used for learning optimal architecture during training. It uses evolutionary algorithms to generate the topology of artificial neural networks and its parameters. The main benefits are…

Sequential data - ranging from financial time series to natural language - has driven the growing adoption of autoregressive models. However, these algorithms rely on the presence of underlying patterns in the data, and their identification…

Plasticity and stability are needed in class-incremental learning in order to learn from new data while preserving past knowledge. Due to catastrophic forgetting, finding a compromise between these two properties is particularly challenging…

Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literature uses key terms like "universal" and "general-purpose"…

Edge camera-based systems are continuously expanding, facing ever-evolving environments that require regular model updates. In practice, complex teacher models are run on a central server to annotate data, which is then used to train…

The rapid evolution of technology has transformed business operations and customer interactions worldwide, with personalization emerging as a key opportunity for e-commerce companies to engage customers more effectively. The application of…

Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…

We study the design decisions of publicly available instruction tuning methods, and break down the development of Flan 2022 (Chung et al., 2022). Through careful ablation studies on the Flan Collection of tasks and methods, we tease apart…

The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However,…

Network embedding is a method to learn low-dimensional representation vectors for nodes in complex networks. In real networks, nodes may have multiple tags but existing methods ignore the abundant semantic and hierarchical information of…

We present in this paper a new approach for polyphonic music transcription using evolution strategies (ES). Automatic music transcription is a complex process that still remains an open challenge. Using an audio signal to be transcribed as…

Recently, one-stage trackers that use a joint model to predict both detections and appearance embeddings in one forward pass received much attention and achieved state-of-the-art results on the Multi-Object Tracking (MOT) benchmarks.…

Large Language Models (LLMs) require precise alignment with complex instructions to optimize their performance in real-world applications. As the demand for refined instruction tuning data increases, traditional methods that evolve simple…

Many biological processes have been the source of inspiration for heuristic methods that generate high-quality solutions to solve optimization and search problems. This thesis presents an epigenetic technique for Evolutionary Algorithms,…

Multivariate testing has recently emerged as a promising technique in web interface design. In contrast to the standard A/B testing, multivariate approach aims at evaluating a large number of values in a few key variables systematically.…

We show that neural networks trained by evolutionary reinforcement learning can enact efficient molecular self-assembly protocols. Presented with molecular simulation trajectories, networks learn to change temperature and chemical potential…

Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely…

Optimizing functions without access to gradients is the remit of black-box methods such as evolution strategies. While highly general, their learning dynamics are often times heuristic and inflexible - exactly the limitations that…