39 citations · 175 across the 48 of their papers we have counts for
12 papers · 1 filter
ECO: Energy-Constrained Operator Learning for Chaotic Dynamics with Boundedness Guarantees
Andrea Goertzen, Sunbochen Tang, Navid Azizan
Chaos is a fundamental feature of many complex dynamical systems, including weather systems and fluid turbulence. These systems are inherently difficult to predict due to their ext…
Efficient Multi-Adapter LLM Serving via Cross-Model KV-Cache Reuse with Activated LoRA
Allison Li, Kristjan Greenewald, Thomas Parnell +1
Modern large language model (LLM) systems increasingly rely on multi-turn pipelines that are composed of multiple task-specific adapters, yet existing serving frameworks remain ine…
ATOM-CBF: Adaptive Safe Perception-Based Control under Out-of-Distribution Measurements
Kai S. Yun, Navid Azizan
Ensuring the safety of real-world systems is challenging, especially when they rely on learned perception modules to infer the system state from high-dimensional sensor data. These…
HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
Zeyang Li, Kaveh Alim, Navid Azizan
Diffusion and flow-matching have emerged as powerful methodologies for generative modeling, with remarkable success in capturing complex data distributions and enabling flexible gu…
Personalized Collaborative Learning with Affinity-Based Variance Reduction
Chenyu Zhang, Navid Azizan
Multi-agent learning faces a fundamental tension: leveraging distributed collaboration without sacrificing the personalization needed for diverse agents. This tension intensifies w…
Hierarchical Vision-Language Planning for Multi-Step Humanoid Manipulation
André Schakkal, Ben Zandonati, Zhutian Yang +1
Enabling humanoid robots to reliably execute complex multi-step manipulation tasks is crucial for their effective deployment in industrial and household environments. This paper pr…
Test-Time-Scaling for Zero-Shot Diagnosis with Visual-Language Reasoning
Ji Young Byun, Young-Jin Park, Navid Azizan +1
As a cornerstone of patient care, clinical decision-making significantly influences patient outcomes and can be enhanced by large language models (LLMs). Although LLMs have demonst…
Know What You Don't Know: Uncertainty Calibration of Process Reward Models
Young-Jin Park, Kristjan Greenewald, Kaveh Alim +2
Process reward models (PRMs) play a central role in guiding inference-time scaling algorithms for large language models (LLMs). However, we observe that even state-of-the-art PRMs…
Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models
Young Jin Park, Francois Germain, Jing Liu +6
Decision-making in building energy systems critically depends on the predictive accuracy of relevant time-series models. In scenarios lacking extensive data from a target building,…
Eluder-Dimension-Free Regret for Stage-Wise Constrained Contextual Bandits via Offline Regression
Haichen Hu, David Simchi-Levi, Navid Azizan
Contextual bandits with stage-wise constraints model decisions that must control risk while learning from their outcomes. We study this problem when only the selected action's rewa…
Activation-Informed Merging of Large Language Models
Amin Heyrani Nobari, Kaveh Alim, Ali ArjomandBigdeli +3
Model merging, a method that combines the parameters and embeddings of multiple fine-tuned large language models (LLMs), offers a promising approach to enhance model performance ac…
On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning
Haoyuan Sun, Ali Jadbabaie, Navid Azizan
Transformer-based models demonstrate a remarkable ability for in-context learning (ICL), where they can adapt to unseen tasks from a few prompt examples without parameter updates.…