paper-conference

[ICLR 2026] Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts

In this work, we study sequential decision-making problem when these preference weights are unobserved latent variables that drift with context.

Xianwei Cao, Dou Quan, Zhenliang Zhang, Shuang Wang

[AAAI 2026] Reasoning with Exploration: An Entropy Perspective

In this work, we revisit entropy–a signal of exploration in RL–and examine its relationship to exploratory reasoning in LMs.

Daixuan Cheng, Shaohan Huang, Xuekai Zhu, Bo Dai, Xin Zhao, Zhenliang Zhang, Furu Wei

[AAAI 2026] Reasoning with Exploration: An Entropy Perspective

[NeurIPS 2025 Workshop] ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making

We propose ValuePilot, a two-phase value-driven decision-making framework comprising a dataset generation toolkit DGT and a decision-making module DMM trained on the generated data.

Yitong Luo, Hou Hei Lam, Ziang Chen, Zhenliang Zhang, Xue Feng

[NeurIPS 2025 Workshop] ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making

[EMNLP 2025] On Domain-Adaptive Post-Training for Multimodal Large Language Models

This paper systematically investigates domain adaptation of MLLMs via post-training, focusing on data synthesis, training pipeline, and task evaluation.

Daixuan Cheng, Shaohan Huang, Ziyu Zhu, Xintong Zhang, Wayne Xin Zhao, Zhongzhi Luan, Bo Dai, Zhenliang Zhang

[EMNLP 2025] On Domain-Adaptive Post-Training for Multimodal Large Language Models

[MM 2024] In Situ 3D Scene Synthesis for Ubiquitous Embodied Interfaces

In this paper, we propose a scene agent that synthesizes situated 3D virtual scenes as a kind of ubiquitous embodied interface in VR for users. The scene agent synthesizes scenes by perceiving the user’s physical environment as well as inferring the user’s demands.

Haiyan Jiang, Leiyu Song, Dongdong Weng, Zhe Sun, Huiying Li, Xiaonuo Dongye, Zhenliang Zhang

[MM 2024] In Situ 3D Scene Synthesis for Ubiquitous Embodied Interfaces

[ICLR 2024] Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World

In this paper, We introduce Bongard-OpenWorld, a new benchmark for evaluating real-world few-shot reasoning for machine vision.

Rujie Wu, Xiaojian Ma, Zhenliang Zhang, Wei Wang, Qing Li, Song-Chun Zhu, Yizhou Wang

[ICLR 2024] Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World

[VR 2024] On the Emergence of Symmetrical Reality

In this paper, we introduce the symmetrical reality framework, which offers a unified representation encompassing various forms of physical-virtual amalgamations.

Zhenliang Zhang, Zeyu Zhang, Ziyuan Jiao, Yao Su, Hangxin Liu, Wei Wang, Song-Chun Zhu

[VR 2024] On the Emergence of Symmetrical Reality

[UIST 2023] Neighbor-Environment Observer: An Intelligent Agent for Immersive Working Companionship

In this paper, we propose a joint observation strategy for artificial agents to support users across virtual and physical environments.

Zhe Sun, Qixuan Liang, Meng Wang, Zhenliang Zhang

[UIST 2023] Neighbor-Environment Observer: An Intelligent Agent for Immersive Working Companionship

[VR 2023] Building symmetrical reality systems for cooperative manipulation

In this paper, we discuss the symmetrical reality-based human-robot interaction and show the general pipeline of building the symmetrical reality system with two minds.

Zhenliang Zhang

[VR 2023] Building symmetrical reality systems for cooperative manipulation

[VR 2021] Symmetrical cognition between physical humans and virtual agents

In this paper, we discuss the cognition problem from some perspectives, i.e., attention, perception, pattern recognition, and communication.

Zhenliang Zhang

[VR 2021] Symmetrical cognition between physical humans and virtual agents