End-to-End Task-Oriented Dialog Modeling With Semi-Structured Knowledge Management

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.

Vision-Language Pre-training (VLP) has advanced the performance of many visionlanguage tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in English. Previous w ...

Under resource constraints, LLMs are usually fine-tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new t ...

Natural language processing and other artificial intelligence fields have witnessed impressive progress over the past decade. Although some of this progress is due to algorithmic advances in deep learning, the majority has arguably been enabled by scaling ...

Informed by longstanding artistic practice, this doctoral thesis approaches entanglements of Swiss coloniality in Brazil and Switzerland under the lens of land, archive, and visuality. The enduring legacies of imperial capitalism in the former Colonia Leop ...

Abstractive summarization has seen big improvements in recent years, mostly due to advances in neural language modeling, language model pretraining, and scaling models and datasets. While large language models generate summaries that are fluent, coherent, ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

Motivation is a multifaceted phenomenon that we explore within the framework of decision-making. Through this cognitive process, actions are directed towards specific goals by performing a trade-off between the cost and benefit of an action. The dorsomedia ...

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimen ...

Text-to-image models, such as Stable Diffusion, can generate high-quality images from simple textual prompts. With methods such as Textual Inversion, it is possible to expand the vocabulary of these models with additional concepts, by learning the vocabula ...

Geomembrane systems have been used at hydropower plants as rehabilitation and mitigation technology for several decades and are now used worldwide. In the context of planning an energy transition that promotes the sustainable use of water resources for ene ...

Investigating the intangible nature of a cultural domain can take multiple forms, addressing for example the aesthetic, epistemic and social dimensions of its phenomenology. The context of Southern Chinese martial arts is of particular significance as it c ...

Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly versatile models in co ...

Sharpness-aware minimization (SAM) has been shown to improve the generalization of neural networks. However, each SAM update requires sequentially computing two gradients, effectively doubling the per-iteration cost compared to base optimizers like SGD. We ...

Time has always been a central factor in understanding the challenges of daily mobility. For a long time, and still today, methods of economic evaluation of transport projects have monetized time savings so that they can be included in the cost–benefit ana ...

The last two decades have seen the development of organoid models for many different tissues and organs. Organoids are three-dimensional organ-mimetics derived from stem or progenitor cells comprising various specialized cell types, resembling the architec ...

Over the years, clinical institutes accumulated large amounts of digital slides from resected tissue specimens. These digital images, called whole slide images (WSIs), are high-resolution tissue snapshots that depict the complex interaction of cells at the ...

Weight-based model editing methods update the parametric knowledge of language models post-training. However, these methods can unintentionally alter unrelated parametric knowledge representations, potentially increasing the risk of harm. In this work, we ...

End-to-End Task-Oriented Dialog Modeling With Semi-Structured Knowledge Management

Chat with Graph Search

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Text Representation Learning for Low Cost Natural Language Understanding

Echoing Swiss Coloniality. Land, Archive and Visuality between Brazil and Switzerland

Interpretable Representation Learning and Evaluation for Abstractive Summarization

Transformer Models for Vision

Neurobiological and metabolic basis of motivation and effort-based decision-making - A human 1H-MRS, fMRI and machine learning study

The multimodality cell segmentation challenge: toward universal solutions

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text

A comprehensive review on geomembrane systems application in hydropower

The Facets of Intangible Heritage in Southern Chinese Martial Arts: Applying a Knowledge-Driven Cultural Contact Detection Approach

4M: Massively Multimodal Masked Modeling

SAMPa: Sharpness-aware Minimization Parallelized

Appropriations and Uses of Travel Time

Bioengineering functional organoid models across scales

Self-Supervised Learning for Patient Stratification and Survival Analysis in Computational Pathology: An Application to Colorectal Cancer

“Flex Tape Can't Fix That”: Bias and Misinformation in Edited Language Models