27 papers
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona +2
Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic deficiencies in ke…
Early Estimation of Language to Latent Alignment in Diffusion Models
Vasco Ramos, Regev Cohen, Idan Szpektor +1
Conditional diffusion models frequently suffer from language-image misalignments. Due to the ambiguity of intermediate noise corrupted latents, assessing prompt adherence currently…
Cross-Lingual Exploration for Parametric Knowledge
Elisha Diskind, Itamar Trainin, Uri Shaham +3
Parametric knowledge in Large Language Models is not equally accessible across languages. As a result, standard inference techniques often struggle to surface localized facts, lead…
Real-Time Execution with Autoregressive Policies
Sangkyu Lee, Seohyeon Park, Tackgeun You +4
Real-time execution, enabled by asynchronous inference that ensures both smooth action trajectories and fast reactivity, is critical for realistic deployments of large-scale Vision…
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
Yue Zhang, Zun Wang, Han Lin +3
Spatial reasoning is a fundamental capability for vision-language models (VLMs) deployed in real-world environments. However, visual observations are inherently limited representat…
Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
Haitong Ma, Ofir Nabati, Aviv Rosenberg +7
Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discre…