4 papers
Optimizing Teacher-Student Partitioning for Scalable Knowledge Distillation on HPC Systems
Adrian P. Dieguez, Victor Conchello Vendrell, Alex Batlle +3
Knowledge Distillation (KD) enables training smaller student models under the guidance of larger teacher models, and the widely adopted TRL library implements it. Yet, TRL treats b…
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
Victor Conchello Vendrell, Arnau Padres Masdemont, Niccolò Grillo +3
Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without generating intermedia…
GameTalk: Training LLMs for Strategic Conversation
Victor Conchello Vendrell, Max Ruiz Luyten, Mihaela van der Schaar
Strategic decision-making in multi-agent settings is a key challenge for large language models (LLMs), particularly when coordination and negotiation must unfold over extended conv…
M3Kang: Evaluating Multilingual Multimodal Mathematical Reasoning in Vision-Language Models
Aleix Torres-Camps, Nathaniel Mitrani Hadida, VÃctor Conchello Vendrell +3
Despite state-of-the-art vision-language models (VLMs) have demonstrated strong reasoning capabilities, their performance in multilingual mathematical reasoning remains underexplor…