Publications

You can also find my articles and citation records on my Google Scholar profile.

Selected Publications and Submissions

Large Models, VLA, Robot Learning, and Agents

  1. TAPO: Dynamic Teacher and Perturbed Answer Injection for Policy Optimization
    Maowei Jiang, et al.
    AAAI 2026 Oral.
    LLM policy optimization with dynamic teacher signals and perturbed answer injection.

  2. FutureVLA: Acting on Predicted Futures with Vision-Language-Action Models
    Maowei Jiang, et al.
    NeurIPS 2026 under review.
    Future-conditioned VLA framework connecting visual world-model prediction and robot action generation.

  3. ReCon: Reference-Conditioned Online Refinement for Vision-Language-Action Policies
    Maowei Jiang, et al.
    NeurIPS 2026 under review.
    Online residual correction for frozen VLA policies on real-robot contact-rich tasks.

  4. Prompt2Act: Mapping Prompts into Sequence of Robotic Actions with Large Foundation Models
    Maowei Jiang, et al.
    Information Fusion, IF 15.5, Q1 Top, CCF-B.
    [GitHub]
    Natural-language prompts to executable robot action sequences.

  5. FDVLA: A Flow-Diffusion Vision-Language-Action Framework with Dual Reasoning Modulation
    Maowei Jiang, et al.
    Information Fusion under review.
    [GitHub]
    Flow-diffusion VLA modeling and reasoning modulation for robot manipulation.

  6. RL2VLA: Reinforcement Learning Fine-tuning for Vision-Language-Action Models
    Maowei Jiang, et al.
    ACM MM 2026 under review.
    [GitHub]
    Reinforcement learning fine-tuning for VLA models.

Representation Learning and Multimodal Generation

  1. DAAC: Discrepancy-Aware Adaptive Contrastive Learning
    Maowei Jiang, et al.
    NeurIPS 2025.
    Adaptive contrastive learning under distribution discrepancy.

  2. CARD: Cross-modal Agent Framework for Generative and Editable Residential Design
    NeurIPS 2024 Workshop on Open-World Agents.
    Cross-modal agents for generative and editable design.

  3. MRED-14: A Benchmark for Low-Energy Residential Floor Plan Generation with 14 Flexible Inputs
    ACM Multimedia.
    Benchmarking controllable low-energy residential floor-plan generation.

  4. GreenPlanner: Practical Floorplan Layout Generation via an Energy-Aware and Function-Feasible Generative Framework
    CVPR.
    Energy-aware and function-feasible generative layout planning.