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
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.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.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.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.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.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
DAAC: Discrepancy-Aware Adaptive Contrastive Learning
Maowei Jiang, et al.
NeurIPS 2025.
Adaptive contrastive learning under distribution discrepancy.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.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.GreenPlanner: Practical Floorplan Layout Generation via an Energy-Aware and Function-Feasible Generative Framework
CVPR.
Energy-aware and function-feasible generative layout planning.
