I am interested in both applied and theoretical research in the domains of deep learning and generative AI. Though my most recent work has been of applied nature, I love theory and finding problems that can benefit from theoretical insights. My interests are diverse.

• LLMs in multi-agent settings. What helps or hinders the performance of LLMs multi-agents system? How to incentivize collaboration among agents? What solution concepts are good for measuring the performance of the multi-agent system? What role do biases play? How to ensure a group of agents behave collectively as expected? Does some unforeseen emergent behavior occur?

• Flow-based models. Theoretical insights, scalability, control, inference efficiency, applications on different domains, alignment, etc. Particular focus on both diffusion models and flow matching.

• Enhancing reasoning and planning capabilities of LLMs. 

• Trustworthiness, safety and security in LLM-based systems.

• Alternative language models. State-space models, text diffusion models, etc.

• Emergent generative models that are different than the mainstream ones.

From my postdoc work, I am interested in theoretical research that helps us better understand the empirical success of machine learning (ML), and that helps us design better ML algorithms with provable guarantees.

• Multi-agent reinforcement learning (RL). How can multiple RL agents be used to benefit the accuracy and/or efficiency of RL algorithms that otherwise would have been done using a single agent? How can we formally justify the use of heuristics that perform well in multi-agent RL solutions? 

• Deep learning foundations. What theoretical insights and guarantees can we provide on the training and generalization of different deep learning models (classic neural networks, LLMs, neural operators, etc.)? What is the role of the training optimizer, normalization procedure, initialization schemes, or any heuristic used during training? How do different hyperparameters affect the interplay among training, generalization and robustness?

From my PhD work, I am interested in the areas of network systems and/or multi-agent systems, where I have studied diverse models by drawing concepts from dynamical systems, game theory, optimization theory and mathematical sociology. I have had collaborators from diverse fields. Some of my works are summarized in the abstract of a talk (link) I gave at UIUC.

• Modeling of social processes. Evolution of positive and negative interpersonal relationships over a social network (social balance theory).  Diffusion of opinion dynamics over (hyper)graphs.

• Stability tools with applications to multi-agent or network systems. Use of the contraction theory stability concept.

• Distributed optimization.

• Epidemic models.

• Distributionally robust optimization.

• Optimal transport and Wasserstein barycenters.

Other Interests:

Other areas I would love to explore are multi-modal AI models, computational economics, and robotics (learning in robotics, embodied intelligence, smart motion planning, multi-robot systems, etc.). 

Preprints:

• Q. Li*, P. Cisneros-Velarde*, K. Fu, S. A. Miranda, S. Vaswani, H. Zhang, "CAT-Flow: Curvature-Adaptive sTeps for Flow Matching", 2026 

• P. Cisneros-Velarde, "Can One-sided Arguments Lead to Response Change in Large Language Models?", 2026.

• P. Cisneros-Velarde, "It Takes Two to Tango: Two Parallel Samplers Improve Quality in Diffusion Models for Limited Steps," 2025.

• S. Zhu, D. Zhang, P. Cisneros-Velarde, J. You, "GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare", 2025

• P. Cisneros-Velarde, “Large Language Models can Achieve Social Balance," 2024.

• A. Attali, P. Cisneros-Velarde, M. Morales and N. Amato, “Discrete State-Action Abstraction via the Successor Representation," 2022.

Published:

• P. Cisneros-Velarde, “Policy Compliance of User Requests in Natural Language for AI Systems ,"  The 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026.

• P. Cisneros-Velarde, “Bypassing Safety Guardrails in LLMs Using Humor," Workshop on LLM security at The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025.

• P. Cisneros-Velarde, B. Shrimali, A. Banerjee, "Optimization for Neural Operators can Benefit from Width," International Conference on Machine Learning  (ICML), 2025. 

• P. Cisneros-Velarde, "Biases in Opinion Dynamics in Multi-Agent Systems of Large Language Models: A Case Study on Funding Allocation," Findings of the Association for Computational Linguistics: NAACL, 2025.

• P. Cisneros-Velarde, Z. Chen, S. Koyejo, A. Banerjee, "Optimization and Generalization Guarantees for Weight Normalization," Transactions on Machine Learning Research (TMLR), 2025.

• P. Cisneros-Velarde, Sanmi Koyejo, "Finite-sample Guarantees for Nash Q-learning with Linear Function Approximation," Uncertainty in Artificial Intelligence (UAI), 2023.

• A Banerjee, P. Cisneros-Velarde, L. Zhu and M Belkin, “Neural tangent kernel at initialization: linear width suffices,” Uncertainty in Artificial Intelligence (UAI), 2023.

• A. Banerjee, P. Cisneros-Velarde, L. Zhu, M. Belkin, “Restricted Strong Convexity of Deep Learning Models with Smooth Activations," International Conference on Learning Representations (ICLR), 2023.

• P. Cisneros-Velarde, B. Lyu, S. Koyejo and M. Kolar, “One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning," International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.

• P. Cisneros-Velarde and F. Bullo, “Distributed Wasserstein Barycenters via Displacement Interpolation,” IEEE Transactions on Control  of Network Systems,  2022.

• P. Cisneros-Velarde and F. Bullo, “A Contraction Theory Approach to Optimization Algorithms from Acceleration Flows,” International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.

• Francesco Bullo, Pedro Cisneros-Velarde, Alexander Davydov, Saber Jafarpour, "From contraction theory to fixed point algorithms on Riemannian and non-Euclidean spaces," 60th IEEE Conference on Decision and Control (CDC), 2021.

• P. Cisneros-Velarde, S. Jafarpour and F. Bullo, “Contraction Theory for Dynamical Systems on Hilbert Spaces,” IEEE Transactions on Automatic Control, 2021.

• P. Cisneros-Velarde and F. Bullo, “Multi-group SIS Epidemics with Simplicial and Higher-Order Interactions,” IEEE Transactions on Control  of Network Systems, 2021.

• P. Cisneros-Velarde, S. Jafarpour and F. Bullo, “Distributed and time-varying primal-dual dynamics via contraction analysis,” IEEE Transactions on Automatic Control, 2021.

• P. Cisneros-Velarde and F. Bullo, “A Network Formation Game for the Emergence of Hierarchies,” PloS One, 2021.

• S. Jafarpour, P. Cisneros-Velarde and F. Bullo, “Weak and Semi-Contraction Theory with Application to Network Systems,” IEEE Transactions on Automatic Control, 2021.

• P. Cisneros-Velarde, K. S. Chan, and F. Bullo, “Polarization and Fluctuations in Signed Social Networks,” IEEE Transactions on Automatic Control, 2020.

• P. Cisneros-Velarde, N. E. Friedkin, A. V. Proskurnikov, F. Bullo, ”Structural Balance via Gradient Flows over Signed Graphs,” IEEE Transactions on Automatic Control, 2020.

• P. Cisneros-Velarde, S. Y. Oh, and A. Petersen, “Distributionally Robust Formulation and Model Selection for the Graphical Lasso,” International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.

• P. Cisneros-Velarde and F. Bullo, ”Signed Network Formation Games and Clustering Balance,” Dynamic Games and Applications, 2020.

• W. Mei, P. Cisneros-Velarde, G. Chen, N. E. Friedkin and F. Bullo, ”Dynamic social balance and convergent appraisals via homophily and influence mechanisms,” Automatica, 2019.

• P. Cisneros-Velarde, D. Oliveira, and K. Chan, ”Spread and Control of Misinformation with Heterogeneous Agents,” International Workshop on Complex Networks, 2019.