papers

Publications (12)

cs.AI2026

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Guibin Zhang, Hejia Geng, Xiaohang Yu +22

The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LL…

cs.CV2023

ImmersiveNeRF: Hybrid Radiance Fields for Unbounded Immersive Light Field Reconstruction

Xiaohang Yu, Haoxiang Wang, Yuqi Han +3

This paper proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolatio…

cs.CR2024

opML: Optimistic Machine Learning on Blockchain

KD Conway, Cathie So, Xiaohang Yu +1

The integration of machine learning with blockchain technology has witnessed increasing interest, driven by the vision of decentralized, secure, and transparent AI services. In thi…

cs.CR2026

SUDP: Secret-Use Delegation Protocol for Agentic Systems

Xiaohang Yu, Hejia Geng, Xinmeng Zeng +1

Agentic systems increasingly act with user secrets for APIs, messaging platforms, and cloud services. Today's agent runtimes typically implement authorization by exposure: enabling…

cs.CV2024

Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience

Xiaohang Yu, Zhengxian Yang, Shi Pan +8

We have built a custom mobile multi-camera large-space dense light field capture system, which provides a series of high-quality and sufficiently dense light field images for vario…

cs.CR2024

opp/ai: Optimistic Privacy-Preserving AI on Blockchain

Cathie So, KD Conway, Xiaohang Yu +2

The convergence of Artificial Intelligence (AI) and blockchain technology is reshaping the digital world, offering decentralized, secure, and efficient AI services on blockchain pl…

cs.CV2023

Super-NeRF: View-consistent Detail Generation for NeRF super-resolution

Yuqi Han, Tao Yu, Xiaohang Yu +2

The neural radiance field (NeRF) achieved remarkable success in modeling 3D scenes and synthesizing high-fidelity novel views. However, existing NeRF-based methods focus more on th…

cs.CR2026

LOCARD: An Agentic Framework for Blockchain Forensics

Xiaohang Yu, William Knottenbelt

Blockchain forensics inherently involves dynamic and iterative investigations, while many existing approaches primarily model it through static inference pipelines. We propose a pa…

cs.LG2026

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning

Zelin Tan, Hejia Geng, Xiaohang Yu +14

While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement learning (RL) post-training remains largel…

cs.CV2026

FMPose3D: monocular 3D pose estimation via flow matching

Ti Wang, Xiaohang Yu, Mackenzie Weygandt Mathis

Monocular 3D pose estimation is fundamentally ill-posed due to depth ambiguity and occlusions, thereby motivating probabilistic methods that generate multiple plausible 3D pose hyp…

cs.CV2026

PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptation

Xiaohang Yu, Ti Wang, Mackenzie Weygandt Mathis

We present PRIMA (*PRI*ors for *M*esh *A*daptation), a framework for robust 3D quadruped mesh recovery under severe species and pose imbalance. Existing animal reconstruction metho…

math.DS2025

On the Periodic Orbits of the Dual Logarithmic Derivative Operator

Xiaohang Yu, William Knottenbelt

We study the periodic behaviour of the dual logarithmic derivative operator in a complex analytic setting. We show that $\mathcal{A…