21 papers
Personalized Federated Direct Preference Optimization via LoRA Adapters
Zhanhong Jiang, Soumik Sarkar
Federated Direct Preference Optimization (FedDPO) enables privacy-preserving alignment of language models across distributed agents without centralizing sensitive preference data.…
Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting
Muhammad Bilal Shahid, Zhanhong Jiang, Soumik Sarkar +1
Long-horizon spacecraft trajectory forecasting suffers from error accumulation due to the absence of corrective observations in the forecast regime, making reliable uncertainty est…
Lighting-aware Unified Model for Instance Segmentation
Qisai Liu, Alloy Das, Zhanhong Jiang +4
Foundation models like the Segment Anything Model (SAM) demonstrate impressive zero-shot generalization but frequently degrade under diverse real-world illumination, particularly f…
TabQL: In-Context Q-Learning with Tabular Foundation Models
Qisai Liu, Zhanhong Jiang, Timilehin Ayanlade +4
We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) with a tabular foundation mod…
COOPO: Cyclic Offline-Online Policy Optimization Algorithm
Qisai Liu, Zhanhong Jiang, Joshua Russell Waite +3
Offline reinforcement learning struggles with distributional shift and constrained performance due to static dataset limitations, while online RL demands prohibitive environment in…
Uncertainty-aware neural emulation reveals climate-resilient maize traits at scale
Mojdeh Saadati, Juan Panelo, Gustavo Visentini +3
Global food security depends on predicting crop responses to climate variability, yet process based crop models remain too computationally expensive for large scale exploration of…
ADKO: Agentic Decentralized Knowledge Optimization
Lucas Nerone Rillo, Zhanhong Jiang, Nastaran Saadati +4
We present Agentic Decentralized Knowledge Optimization (ADKO), a framework for collaborative black-box optimization across autonomous agents that achieves sample efficiency, priva…
Neural CDEs as Correctors for Learned Time Series Models
Muhammad Bilal Shahid, Zhanhong Jiang, Prajwal Koirala +2
Learned time-series models, whether continuous or discrete, are widely used for forecasting the states of dynamical systems but suffer from error accumulation in multi-step forecas…
Balancing Utility and Privacy: Dynamically Private SGD with Random Projection
Zhanhong Jiang, Md Zahid Hasan, Nastaran Saadati +3
Stochastic optimization is a pivotal enabler in modern machine learning, producing effective models for various tasks. However, several existing works have shown that model paramet…
Decentralized Relaxed Smooth Optimization with Gradient Descent Methods
Zhanhong Jiang, Aditya Balu, Soumik Sarkar
-smoothness, which has been pivotal to advancing decentralized optimization theory, is often fairly restrictive for modern tasks like deep learning. The recent advent of relax…
Data-driven Kinematic Modeling in Soft Robots: System Identification and Uncertainty Quantification
Zhanhong Jiang, Dylan Shah, Hsin-Jung Yang +1
Precise kinematic modeling is critical in calibration and controller design for soft robots, yet remains a challenging issue due to their highly nonlinear and complex behaviors. To…
DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation Models
Nastaran Saadati, Zhanhong Jiang, Joshua R. Waite +4
Low-Rank Adaptation (LoRA) has emerged as one of the most effective, computationally tractable fine-tuning approaches for training Vision-Language Models (VLMs) and Large Language…
SC-NeRF: NeRF-based Point Cloud Reconstruction using a Stationary Camera for Agricultural Applications
Kibon Ku, Talukder Z Jubery, Elijah Rodriguez +4
This paper presents a NeRF-based framework for point cloud (PCD) reconstruction, specifically designed for indoor high-throughput plant phenotyping facilities. Traditional NeRF-bas…
Bidirectional Linear Recurrent Models for Sequence-Level Multisource Fusion
Qisai Liu, Zhanhong Jiang, Joshua R. Waite +3
Sequence modeling is a critical yet challenging task with wide-ranging applications, especially in time series forecasting for domains like weather prediction, temperature monitori…
FUSE: First-Order and Second-Order Unified SynthEsis in Stochastic Optimization
Zhanhong Jiang, Md Zahid Hasan, Aditya Balu +3
Stochastic optimization methods have actively been playing a critical role in modern machine learning algorithms to deliver decent performance. While numerous works have proposed a…
Enhancing PPO with Trajectory-Aware Hybrid Policies
Qisai Liu, Zhanhong Jiang, Hsin-Jung Yang +3
Proximal policy optimization (PPO) is one of the most popular state-of-the-art on-policy algorithms that has become a standard baseline in modern reinforcement learning with applic…
RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception
Joshua R. Waite, Md. Zahid Hasan, Qisai Liu +3
Vision-language model (VLM) fine-tuning for application-specific visual grounding based on natural language instructions has become one of the most popular approaches for learning-…
FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning
Prajwal Koirala, Zhanhong Jiang, Soumik Sarkar +1
Safe offline reinforcement learning aims to learn policies that maximize cumulative rewards while adhering to safety constraints, using only offline data for training. A key challe…
Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
Prajwal Koirala, Zhanhong Jiang, Soumik Sarkar +1
In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only of…
DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models
Nastaran Saadati, Minh Pham, Nasla Saleem +5
Recent advances in decentralized deep learning algorithms have demonstrated cutting-edge performance on various tasks with large pre-trained models. However, a pivotal prerequisite…
Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing
A K Nirala, A Joshi, C Hegde +1
A key benefit of deep vision-language models such as CLIP is that they enable zero-shot open vocabulary classification; the user has the ability to define novel class labels via na…