Skip to content

Author

Jia Liu

We have 7 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Nov 2026

From Bellman to Boltzmann: Towards a Kinetic Theory of Controlled Emergence and Meta-Cognition

We propose a research vision for a kinetic theory of collective intelligence in large-scale multi-agent learning systems. Contemporary multi-agent reinforcement learning (MARL) provides powerful tools for optimizing individual agents, while mean-field game theory characterizes population-level decision-making in the la...

Jia Liu, Alvaro Velasquez, Susmit Jha et al. · 0 citations
#machine learning Preprint Nov 2026

BiMuon: A Geometry-Aware Stochastic Bilevel Optimization Approach

Stochastic bilevel optimization provides a general framework for many machine learning applications, such as hyperparameter learning, data reweighting, language model alignment, and actor-critic reinforcement learning. However, most existing bilevel optimization methods treat matrix-valued gradients as flattened vector...

Zhen Qin, Zhi-Yao Zhang, Ying-Bin Liang et al. · 0 citations
#artificial intelligence Book Open access Oct 2026

Foundation Model-Aided Multi-Agent Reinforcement Learning for Wireless Random Access Network Optimization

Random access (RA) is one of the most foundational medium access control (MAC) layer scheduling schemes for handling unpredictable data traffic from multiple terminals. While multi-agent reinforcement learning (MARL) has been explored to optimize RA-based wireless networks, its reliance on experience-driven, distribute...

Myeung Suk Oh, Zhi-Yao Zhang, Alvaro Velasquez et al. · 0 citations

DEALS: Decentralized Expertise-Aware Load Serving for Multi-Agent LLM Systems

Experiments show that DEALS not only improves performance along multiple dimensions (e.g., answer accuracy and task throughput) in both homogeneous and heterogeneous agent pools, but also balances agent expertise and workload in a self-organized manner, enabling effective decentralized coordination.

Jing-Hang Huang, Wen-Bin Wang, Yan-Chuan Yin et al. · 0 citations
#machine learning Preprint Sep 2026

To Solve Bilevel Optimization with Nonconvex Lower Levels, We Need Second-Order Stationarity

This work is the first to establish the finite-time convergence for achieving lower-level second-order stationary solutions in general LLNC-BLO and proposes the PROBE (Perturbed gradient algorithm for bilevel problem), which achieves a finite-time convergence rate of O(T^{-2/5}) where T denotes iterations.

Zhi-Yao Zhang, Meng-Lu Yu, Alvaro Velasquez et al. · 0 citations
Preprint Aug 2026

Parallelizable Gradient-Based Optimization For Multi-Objective MaxCut

This paper develops a differentiable framework for multi-objective MaxCut by combining an adjacency-based quadratic formulation with linear scalarization, thereby reducing the problem to a preference-conditioned single-objective signed-weight MaxCut problem.

Jing-Hang Huang, Cheng-Han Huang, Alvaro Velasquez et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.