Towards Generalizable Trajectory Prediction using Dual-Level Representation Learning and Adaptive Prompting

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.

While large language models (LLMs) are increasingly playing a pivotal role in education by providing instantaneous, adaptive responses, their potential to promote critical thinking remains understudied. In this paper, we fill such a gap and present an inno ...

How does the brain generate behavioral responses from sensory stimuli? This sensor-to-motor transformation is a fundamental question in systems neuroscience. While recent experiments have highlighted the complexity of neural representations across the cere ...

Decision-making permeates every aspect of human and societal development, from individuals' daily choices to the complex decisions made by communities and institutions. Central to effective decision-making is the discipline of optimization, which seeks th ...

We propose InNeRF360, an automatic system that accurately removes text-specified objects from 360 • Neural Radiance Fields (NeRF). The challenge is to effectively remove objects while inpainting perceptually consistent content for the missing regions, whic ...

This manuscript details and extends the system identification methods leveraging the backpropagation (SIMBa) toolbox presented in previous work, which uses well-established machine learning tools for discrete-time linear multistep-ahead state-space system ...

Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses. However, no studies have shown that instruction-tuning actually teaches LLMs to process langu ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

Regular inspection and maintenance are crucial for ensuring the optimal performance of solar panels. However, conventional manual methods can be laborious, time consuming, and expensive, especially for large and inaccessible installations. Aerial inspectio ...

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 ...

The material composition of asteroids is an essential piece of knowledge in the quest to understand the formation and evolution of the Solar System. Visual to near-infrared spectra or multiband photometry is required to constrain the material composition o ...

Non-linear partial differential Kolmogorov equations are successfully used to describe a wide range of time dependent phenomena, in natural sciences, engineering or even finance. For example, in physical systems, the Allen-Cahn equation describes pattern f ...

Machine learning and data processing algorithms have been thriving in finding ways of processing and classifying information by exploiting the hidden trends of large datasets. Although these emerging computational methods have become successful in today's ...

The ubiquity of distributed machine learning (ML) in sensitive public domain applications calls for algorithms that protect data privacy, while being robust to faults and adversarial behaviors. Although privacy and robustness have been extensively studied ...

Detecting and quantifying marine pollution and macroplastics is an increasingly pressing ecological issue that directly impacts ecology and human health. Here, remote sensing can provide reliable estimates of plastic pollution by regularly monitoring and d ...

Current methods for few-shot fine-tuning of pretrained masked language models (PLMs) require carefully engineered prompts and verbalizers for each new task to convert examples into a cloze-format that the PLM can score. In this work, we propose PERFECT, a ...

Neural networks are ubiquitous in applied machine learning for education. Their pervasive success in predictive performance comes alongside a severe weakness, the lack of explainability of their decisions, especially relevant in human-centric fields. We im ...

Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet in practice, people, no matter how conscientious, have trouble precisely delineating in 3D and on a large scale, in part because the data i ...

Dynamical Systems (DS) are fundamental to the modeling and understanding time evolving phenomena, and have application in physics, biology and control. As determining an analytical description of the dynamics is often difficult, data-driven approaches are ...

Poor decisions and selfish behaviors give rise to seemingly intractable global problems, such as the lack of transparency in democratic processes, the spread of conspiracy theories, and the rise in greenhouse gas emissions. However, people are more predict ...

We study how neural networks compress uninformative input space in models where data lie in d dimensions, but the labels of which only vary within a linear manifold of dimension d(parallel to) < d. We show that for a one-hidden-layer network initialized wi ...

Towards Generalizable Trajectory Prediction using Dual-Level Representation Learning and Adaptive Prompting

Chat with Graph Search

Enhancing Critical Thinking in Education by Means of a Socratic Chatbot

Capturing behavioral and neural variability in multi-area spiking neuronal network models

Reliable data-driven decision-making through optimal transport

InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360° Neural Radiance Fields

SIMBa: System Identification Methods Leveraging Backpropagation

Instruction-tuned LLMs with World Knowledge are More Aligned to the Human Brain

Aggregating Spatial and Photometric Context for Photometric Stereo

Drone‐Based Solar Cell Inspection With Autonomous Deep Learning

18 GHz Ultraviolet Astrocomb via Chip-Integrated Harmonic Generation

Euclid: Identification of asteroid streaks in simulated images using deep learning

Solving Non-linear Kolmogorov Equations in Large Dimensions by Using Deep Learning: A Numerical Comparison of Discretization Schemes

2D Nanosystems: Applications of 2D Semiconductors for In-Memory Computing

On the Privacy-Robustness-Utility Trilemma in Distributed Learning

Large-scale detection of marine debris in coastal areas with Sentinel-2

PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models

Evaluating the Explainers: Black-Box Explainable Machine Learning for Student Success Prediction in MOOCs

Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate

Linearization and Identification of Multiple-Attractor Dynamical Systems through Laplacian Eigenmaps

Discrete-Choice Mining of Social Processes

Geometric compression of invariant manifolds in neural networks