CHAMELEON: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

Large language models (LLMs) are transforming research in psychology and the behavioral sciences by enabling advanced text analysis at scale. Their applications range from the analysis of social media posts to infer psychological traits to the automated sc ...

We introduce BLAP, a model capable of generating high-quality captions for music. BLAP leverages a fine-tuned CLAP audio encoder and a pre-trained Flan-T5 large language model. To achieve effective cross-modal alignment between music and language, BLAP uti ...

Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise effectively. Although deep- ...

Proteins are the molecular machines of life, driving essential biological processes such as enzymatic catalysis, cellular signaling, and immune responses. The ability to design entirely new proteins with desired structures and functions has immense implica ...

This thesis focuses on understanding and improving the reasoning capabilities of neural networks. It develops theoretical results and empirical analyses to uncover reasoning potential and limitations, leveraging these insights to guide the design of improv ...

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliability of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an effort to avoid err ...

Foundation models have become a powerful tool in single-cell transcriptomics, enabling broad generalization across tasks such as cell type annotation, data integration, and drug response prediction. Yet, most current models are trained predominantly on hea ...

Machine learning has transformed many fields and has recently found applications in chemistry and materials science. The small datasets commonly found in chemistry sparked the development of sophisticated machine learning approaches that incorporate chemic ...

Generative artificial intelligence (AI) has made unprecedented advances in vision language models over the past two years. These advances are largely due to diffusion-based generative models, which are very stable and simple to train. These diffusion model ...

Marmoset monkeys encode vital information in their calls and serve as a surrogate model for neuro-biologists to understand the evolutionary origins of human vocal communication. Traditionally analyzed with signal processing-based features, recent approache ...

Over the past years, image generation and manipulation have achieved remarkable progress due to the rapid development of generative AI based on deep learning. Recent studies have devoted significant efforts to address the problem of face image manipulation ...

For our fifth anniversary, we reconnected with authors of recent Comments and Perspectives in Nature Machine Intelligence and asked them how the topic they wrote about developed. We also wanted to know what other topics in AI they found exciting, surprisin ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

Crafting an appealing heading is crucial for attracting readers and marketing work or products. A popular way is to summarize the main idea with a refined description and a memorable acronym. However, there lacks a systematic study and a formal benchmark i ...

The creation of high fidelity synthetic data has long been an important goal in machine learning, particularly in fields like finance where the scarcity of available training and test data make it difficult to utilize many of the deep learning techniques w ...

Monitoring surface cracks in infrastructure is crucial for structural health monitoring. Automatic visual inspection offers an effective solution, especially in hard-to-reach areas. Machine learning approaches have proven their effectiveness but typically ...

We propose a test -time adaptation for 6D object pose tracking that learns to adapt a pre -trained model to track the 6D pose of novel objects. We consider the problem of 6D object pose tracking as a 3D keypoint detection and matching task and present a mo ...

CHAMELEON: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning

Chat with Graph Search

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

From Embeddings to Explainability: A Tutorial on Large-Language-Model-Based Text Analysis for Behavioral Scientists

Bootstrapping Language-Audio Pre-training for Music Captioning

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising

Computational design of complex protein folds and soluble analogs of membrane proteins

Learning to Reason with Neural Networks: Principles and Methods

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation

Abstract IA02: Cancer-specific foundation models: Friend or foe in healthcare AI?

Leveraging large language models for predictive chemistry

MCMC: Bridging Rendering, Optimization and Generative AI

On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis

Towards the Detection of AI-Synthesized Human Face Images

Anniversary AI reflections

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

Sparse autoregressive neural networks for classical spin systems

Unveiling the Art of Heading Design: A Harmonious Blend of Summarization, Neology, and Algorithm

Macroeconomic Conditioned Synthetic Financial Markets

From classification to segmentation with explainable AI: A study on crack detection and growth monitoring

Test-time adaptation for 6D pose tracking