Talks

9:00 Welcome

9:10 Keynote:

Noelia Ferruz (Centre de Regulació Genòmica)

10:00 Session 1

Session Chair: Marco Baroni (ICREA UPF)

Elias Abad Rocamora (EPFL) - Revisiting Character-level Adversarial Attacks for Language Models (ICML 2024)

Matéo Mahaut (UPF) - Memorization and confidence in memorization (ACL 2024)

Juan Haladjian (Apple) - On Efficient and Statistical Quality Estimation for Data Annotation (ACL 2024)

Emily Cheng (UPF) - Bridging Information-Theoretic and Geometric Compression in Language Models (EMNLP 2023)

11:00 Poster Session 1

12:00 Session 2

Session Chair: Jose M. Álvarez (NVidia)

Eduard Trulls (Google) -  SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding

(NeurIPS 2023)

David Serrano-Lozano (CVC) - NamedCurves: Learned Image Enhancement via Color Naming (ECCV 2024)

Gemma Canet Tarrés (University Surrey) - Thinking Outside the BBox: Unconstrained Generative Object Compositing

(ECCV 2024)

Albert Pumarola (Meta) - Movie Gen: A Cast of Media Foundation Models

Guénolé Fiche (CentraleSupélec) - VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space (ECCV 2024)

Ricardo Martin-Brualla (Google) - CAT3D: Create Anything in 3D with Multi-View Diffusion Models (NeurIPS 2024 - Oral)

Alessio Mazzucheli (UPC) - IReNe: Instant Recoloring of Neural Radiance Fields (CVPR 2024)

15:00 Session 3

Session Chair: Fernando de la Torre (CMU) 

David Bonet (Stanford) - HyperFast: Instant Classification for Tabular Data (AAAI 2024)

Alex Gomez-Villa (CVC) - Exemplar-free Continual Representation Learning via Learnable Drift Compensation (ECCV 2024)

Ferran Alet (Deepmind) - GenCast: Diffusion-based ensemble forecasting for medium-range weather (Nature 2024)

German Barquero (UB) - FlowMDM: Seamless Human Motion Composition with Blended Positional Encodings (CVPR 2024)

Yumeng Li (Amazon) - Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive (ICLR 2024)

Konstantin Schürholt (University St. Gällen) - Scalable Weight Space Learning (ICML 2024)

Xavier Suau (Apple) - Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models (ICML 2024)

16:30 Poster Session 2 

17:30 Session 4 

Session Chair: Míriam Bellver (Amazon) 

Gerard Gállego (UPC) - Unveiling the Role of Pretraining in Direct Speech Translation (EMNLP 2024)

Guillermo Cámbara (Amazon) -“Generative Speech Language Modeling for Synthesis and Editing” (related to ICASSP 2024)

Jordi Pons (Stability) - Fast Timing-Conditioned Latent Audio Diffusion (ICML 2024)

Santi Pascual (Dolby) - Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity (ECCV 2024)

18:20 Panel

19:00 Closing