collaborators

10 papers

cs.RO2026

HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies

Zhiying Du, Bei Liu, Yaobo Liang +7

Generalist vision--language--action (VLA) policies are typically trained on heterogeneous mixtures of robot demonstrations spanning diverse embodiments, action spaces, and observat…

cs.RO2026

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data

Zhiyuan Feng, Qixiu Li, Huizhi Liang +12

Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models. However, most existing approaches rely on large…

cs.CV2026

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Keming Wu, Yijing Cui, Wenhan Xue +11

Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet…

cs.CV2026

HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models

Huizhi Liang, Yichao Shen, Yu Deng +5

Achieving human-like spatial intelligence for vision-language models (VLMs) requires inferring 3D structures from 2D observations, recognizing object properties and relations in 3D…

cs.AI2026

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning

Zhaowei Zhang, Xiaohan Liu, Xuekai Zhu +6

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) alignment requires fundamen…

cs.CL2026

HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models

Zhaolu Kang, Junhao Gong, Jiaxu Yan +15

Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains. However, current benchmarks for evaluating MLLMs primarily emp…