21 citations · 39 across the 21 of their papers we have counts for
22 papers
Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL
Yunhao Yang, Yuexin Bian, Yunjie Tian +6
Reinforcement learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-language models, yet its strongest successes still depend heavily on g…
Characterizing Opinion Evolution of Networked LLMs
Caleb Probine, Yigit Ege Bayiz, Filippos Fotiadis +3
Large language models (LLMs) increasingly interact with one another in multi-agent systems, from simulations of human discourse to influence operations and fully LLM-driven social…
What Objects Enable, Not What They Are: Functional Latent Spaces for Affordance Reasoning
Rohan Siva, Neel P. Bhatt, Yunhao Yang +6
Existing robot planning systems rely on appearance-based reasoning, where visual observations are encoded into latent spaces organized around object appearances (e.g., recognizing…
VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents
Yunhao Yang, Neel P. Bhatt, Kevin Wang +3
Reusable robot skills are becoming the basic units through which embodied agents turn open-ended instructions into long-horizon physical behavior. We argue that, while foundation m…
RepV: Safety-Separable Latent Spaces for Scalable Neurosymbolic Plan Verification
Yunhao Yang, Neel P. Bhatt, Pranay Samineni +3
As AI systems migrate to safety-critical domains, verifying that their actions comply with well-defined rules remains a challenge. Formal methods provide provable guarantees but de…
VLN-Zero: Rapid Exploration and Cache-Enabled Neurosymbolic Vision-Language Planning for Zero-Shot Transfer in Robot Navigation
Neel P. Bhatt, Yunhao Yang, Rohan Siva +4
Rapid adaptation in unseen environments is essential for scalable real-world autonomy, yet existing approaches rely on exhaustive exploration or rigid navigation policies that fail…
LAD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback
Yunhao Yang, Junyuan Hong, Gabriel Jacob Perin +4
Large language models (LLMs) can translate natural language instructions into executable action plans for robotics, autonomous driving, and other domains. Yet, deploying LLM-driven…
Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces
Yunhao Yang, Neel P. Bhatt, Christian Ellis +4
Logistics operators, from battlefield coordinators re-routing airlifts ahead of a storm to warehouse managers juggling late trucks, need to make mission-critical decisions. Prevail…
Evaluating Human Trust in LLM-Based Planners: A Preliminary Study
Shenghui Chen, Yunhao Yang, Kayla Boggess +3
Large Language Models (LLMs) are increasingly used for planning tasks, offering unique capabilities not found in classical planners such as generating explanations and iterative re…
Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework
Neel P. Bhatt, Yunhao Yang, Rohan Siva +3
Multimodal foundation models offer a promising framework for robotic perception and planning by processing sensory inputs to generate actionable plans. However, addressing uncertai…
Uncertainty-Guided Enhancement on Driving Perception System via Foundation Models
Yunhao Yang, Yuxin Hu, Mao Ye +5
Multimodal foundation models offer promising advancements for enhancing driving perception systems, but their high computational and financial costs pose challenges. We develop a m…
Fine-Tuning Language Models Using Formal Methods Feedback
Yunhao Yang, Neel P. Bhatt, Tyler Ingebrand +4
Although pre-trained language models encode generic knowledge beneficial for planning and control, they may fail to generate appropriate control policies for domain-specific tasks.…
Specification-Driven Video Search via Foundation Models and Formal Verification
Yunhao Yang, Jean-Raphaël Gaglione, Sandeep Chinchali +1
The increasing abundance of video data enables users to search for events of interest, e.g., emergency incidents. Meanwhile, it raises new concerns, such as the need for preserving…
On the Planning, Search, and Memorization Capabilities of Large Language Models
Yunhao Yang, Anshul Tomar
The rapid advancement of large language models, such as the Generative Pre-trained Transformer (GPT) series, has had significant implications across various disciplines. In this st…
Multimodal Pretrained Models for Verifiable Sequential Decision-Making: Planning, Grounding, and Perception
Yunhao Yang, Cyrus Neary, Ufuk Topcu
Recently developed pretrained models can encode rich world knowledge expressed in multiple modalities, such as text and images. However, the outputs of these models cannot be integ…
Automaton-Based Representations of Task Knowledge from Generative Language Models
Yunhao Yang, Jean-Raphaël Gaglione, Cyrus Neary +1
Automaton-based representations of task knowledge play an important role in control and planning for sequential decision-making problems. However, obtaining the high-level task kno…
Additive Logistic Mechanism for Privacy-Preserving Self-Supervised Learning
Yunhao Yang, Parham Gohari, Ufuk Topcu
We study the privacy risks that are associated with training a neural network's weights with self-supervised learning algorithms. Through empirical evidence, we show that the fine-…
On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Models
Yunhao Yang, Parham Gohari, Ufuk Topcu
We study the privacy implications of training recurrent neural networks (RNNs) with sensitive training datasets. Considering membership inference attacks (MIAs), which aim to infer…
Self-Enhancing Multi-filter Sequence-to-Sequence Model
Yunhao Yang, Zhaokun Xue, Andrew Whinston
Representation learning is important for solving sequence-to-sequence problems in natural language processing. Representation learning transforms raw data into vector-form represen…
Training Heterogeneous Features in Sequence to Sequence Tasks: Latent Enhanced Multi-filter Seq2Seq Model
Yunhao Yang, Zhaokun Xue
In language processing, training data with extremely large variance may lead to difficulty in the language model's convergence. It is difficult for the network parameters to adapt…
Identifying Mislabeled Images in Supervised Learning Utilizing Autoencoder
Yunhao Yang, Andrew Whinston
Supervised learning is based on the assumption that the ground truth in the training data is accurate. However, this may not be guaranteed in real-world settings. Inaccurate traini…
A Survey on Reinforcement Learning for Combinatorial Optimization
Yunhao Yang, Andrew Whinston
This paper gives a detailed review of reinforcement learning (RL) in combinatorial optimization, introduces the history of combinatorial optimization starting in the 1950s, and com…