collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Answer-Level Trust Selection for Physical Vision-Language Reasoning

Rongyu Yu, Ke Niu, Fengxiang He

Vision-language models (VLMs) can estimate physical quantities such as duration, speed, and acceleration from visual observations, but existing benchmarks primarily assess overall…

cs.LG2026

Generalisation of RLHF under Reward Shift and Clipped KL Regularisation

Kenton Tang, Yuzhu Chen, Fengxiang He

Alignment and adaptation in large language models heavily rely on reinforcement learning from human feedback (RLHF); yet, theoretical understanding of its generalisability remains…

cs.LG2026

PRISM: Parallel Reward Integration with Symmetry for MORL

Finn van der Knaap, Kejiang Qian, Zheng Xu +1

This work studies heterogeneous Multi-Objective Reinforcement Learning (MORL), where objectives can differ sharply in temporal frequency. Such heterogeneity allows dense objectives…

cs.LG2026

Rationality Measurement and Theory for Reinforcement Learning Agents

Kejiang Qian, Amos Storkey, Fengxiang He

This paper proposes a suite of rationality measures and associated theory for reinforcement learning agents, a property increasingly critical yet rarely explored. We define an acti…

cs.LG2026

DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on Decentralized Financial Networks

Aijie Shu, Wenbin Wu, Gbenga Ibikunle +1

Credit exposure in Decentralized Finance (DeFi) is often implicit and token-mediated, creating a dense web of inter-protocol dependencies. Thus, a shock to one token may result in…

cs.LG2025

DeXposure: A Dataset and Benchmarks for Inter-protocol Credit Exposure in Decentralized Financial Networks

Wenbin Wu, Kejiang Qian, Alexis Lui +5

We curate the DeXposure dataset, the first large-scale dataset for inter-protocol credit exposure in decentralized financial networks, covering global markets of 43.7 million entri…