Papers by Xiyao Ma
MMPlanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multimodal planning use large language models to refine textual steps, but visual object-state alignment and systematic evaluation are underexplored. |
| Approach: | They propose a multimodal multimodal planning framework that uses a 'object-state reasoning chain-of-thought' system to model object-state transitions and generate accurate multimodal plans. |
| Outcome: | The proposed framework improves textual planning by +6.8% and cross-modal alignment by +11.9%. |
A Batch Normalized Inference Network Keeps the KL Vanishing Away (2020.acl-main)
Copied to clipboard
| Challenge: | Variational Autoencoder (VAE) is widely used to approximate a model’s posterior on latent variables. |
| Approach: | They propose to let the Kullback–Leibler divergence individual follow a distribution across the whole dataset and analyze that it is sufficient to prevent posterior collapse by keeping the expectation of the KL’s distribution positive. |
| Outcome: | The proposed approach can avoid posterior collapse effectively and efficiently without introducing any new model component or modifying the objective. |