7 papers
Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models
Wenhui Tan, Fiorenzo Parascandolo, Enver Sangineto +6
Large Reasoning Models (LRMs) have recently achieved strong mathematical and code reasoning performance through Reinforcement Learning (RL) post-training. However, we show that mod…
ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detection
Mattia Bernardi, Chiara Cappellino, Matteo Mosconi +3
Although recent Open-Vocabulary Object Detection architectures, such as Grounding DINO, demonstrate strong zero-shot capabilities, their performance degrades significantly under do…
BFS-PO: Best-First Search for Large Reasoning Models
Fiorenzo Parascandolo, Wenhui Tan, Enver Sangineto +2
Large Reasoning Models (LRMs) such as OpenAI o1 and DeepSeek-R1 have shown excellent performance in reasoning tasks using long reasoning chains. However, this has also led to a sig…
Guiding the Experts: Semantic Priors for Efficient and Focused MoE Routing
Chengxi Min, Wei Wang, Yahui Liu +4
Mixture-of-Experts (MoE) models have emerged as a promising direction for scaling vision architectures efficiently. Among them, Soft MoE improves training stability by assigning ea…
One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data
Simone Luetto, Fabrizio Garuti, Enver Sangineto +2
There is a recent growing interest in applying Deep Learning techniques to tabular data, in order to replicate the success of other Artificial Intelligence areas in this structured…
Diffusion Transformers for Tabular Data Time Series Generation
Fabrizio Garuti, Enver Sangineto, Simone Luetto +2
Tabular data generation has recently attracted a growing interest due to its different application scenarios. However, generating time series of tabular data, where each element of…