6 papers · 1 filter
Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion
Amirhosein Javadi, Shirin Saeedi Bidokhti, Tara Javidi
Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires controlling the generative proces…
Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery
Halil Alperen Gozeten, Xuechen Zhang, Emrullah Ildiz +3
Recent LLM-guided evolutionary search methods have shown that iterative program mutation can discover strong algorithms, but they typically optimize each task independently, even w…
Active World-Model with 4D-informed Retrieval for Exploration and Awareness
Elaheh Vaezpour, Amirhosein Javadi, Tara Javidi
Physical awareness, especially in a large and dynamic environment, is shaped by sensing decisions that determine observability across space, time, and scale, while observations imp…
Convex and Non-convex Federated Learning with Stale Stochastic Gradients: Diminishing Step Size is All You Need
Xinran Zheng, Tara Javidi, Behrouz Touri
We propose a general framework for distributed stochastic optimization under delayed gradient models. In this setting, local agents leverage their own data and computation to a…
-Explorer: Minimax Active Model Estimation in MDPs
Xihe Gu, Urbashi Mitra, Tara Javidi
Accurately estimating the transition dynamics of an unknown Markov decision process (MDP) is a central problem in reinforcement learning. The accuracy of overall model estimation,…
From Relative Entropy to Minimax: A Unified Framework for Coverage in MDPs
Xihe Gu, Urbashi Mitra, Tara Javidi
Targeted and deliberate exploration of state--action pairs is essential in reward-free Markov Decision Problems (MDPs). More precisely, different state-action pairs exhibit differe…