Talks

9:30 Welcome

9:40 Keynote

José Manuel Álvarez (Nvidia)

10:30 Session 1

Session Chair: Alex Karatzoglou (Amazon)

Invited Speaker 1: Adrià Recasens (Google Deepmind)

Invited Speaker 2: Mafalda Dias (CRG)

Josep López (UOC) - Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent (NeurIPS 2025)

Marius Miron (Earth Species Project) - NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics (ICLR 2025)

Pol Puigdemont (EPFL) - Ascent Fails to Forget (NeurIPS 2025)

11:30 Poster Session 1

12:30 Session 2

Session Chair: LLúís Màrquez (UPC)

Invited Speaker 3: Marta R. Costa-jussà (Meta)

Invited Speaker 4: Noa Garcia (Osaka University)

Gemma Boleda (UPF) - LLMs as a synthesis between symbolic and distributed approaches to language (Findings of ACL 2025)

Oscar Mañas (MILA) - Controlling Multimodal LLMs via Reward-guided Decoding (ICCV 2025)

Lucas Ventura (ParisTech / INRIA) - Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs (CVPR 2025)

13:30 Lunch Break

14:00 Poster Session 2

15:00 Session 3

Session Chair: Gemma Roig (Goethe University)

Invited Speaker 5: David Vázquez (Service Now)

Invited Speaker 6: Maria Bauzà (Google Deepmind)

Guillem Brasó (Nvidia) - Native Segmentation Vision Transformers (NeurIPS 2025)

Danna Xue (CVC) - Accelerating Neural Video Decomposition via Hypernetworks (CVPR 2025)

Angela Lopez-Cardona (Telefonica R&D) - Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models

 (ICLR 2025)

16:00 Poster Session 3 

17:00 Panel

Panelists: Ricardo Baeza-Yates (UPF), Oliver Patel (AstraZeneca). More to announced.

17:45 Closing

18:00 Social event: Torrons & Cava