TY - GEN
T1 - LLaPa
T2 - 33rd ACM International Conference on Multimedia, MM 2025
AU - Sun, Shibo
AU - Li, Xue
AU - Di, Donglin
AU - Wei, Mingjie
AU - Nie, Lanshun
AU - Zhang, Wei Nan
AU - Zhan, Dechen
AU - Song, Yang
AU - Fan, Lei
N1 - Publisher Copyright:
© 2025 ACM.
PY - 2025/10/27
Y1 - 2025/10/27
N2 - While large language models (LLMs) have advanced procedural planning for embodied AI systems through strong reasoning abilities, the integration of multimodal inputs and counterfactual reasoning remains underexplored. To tackle these challenges, we introduce LLaPa, a vision-language model framework designed for multimodal procedural planning. LLaPa generates executable action sequences from textual task descriptions and visual environmental images using vision-language models (VLMs). Furthermore, we enhance LLaPa with two auxiliary modules to improve procedural planning. The first module, the Task-Environment Reranker (TER), leverages task-oriented segmentation to create a task-sensitive feature space, aligning textual descriptions with visual environments and emphasizing critical regions for procedural execution. The second module, the Counterfactual Activities Retriever (CAR), identifies and emphasizes potential counterfactual conditions, enhancing the model's reasoning capability in counterfactual scenarios. Extensive experiments on ActPlan-1K and ALFRED benchmarks demonstrate that LLaPa generates higher-quality plans with superior LCS and correctness, outperforming advanced models. The code and models are available https://github.com/sunshibo1234/LLaPa.
AB - While large language models (LLMs) have advanced procedural planning for embodied AI systems through strong reasoning abilities, the integration of multimodal inputs and counterfactual reasoning remains underexplored. To tackle these challenges, we introduce LLaPa, a vision-language model framework designed for multimodal procedural planning. LLaPa generates executable action sequences from textual task descriptions and visual environmental images using vision-language models (VLMs). Furthermore, we enhance LLaPa with two auxiliary modules to improve procedural planning. The first module, the Task-Environment Reranker (TER), leverages task-oriented segmentation to create a task-sensitive feature space, aligning textual descriptions with visual environments and emphasizing critical regions for procedural execution. The second module, the Counterfactual Activities Retriever (CAR), identifies and emphasizes potential counterfactual conditions, enhancing the model's reasoning capability in counterfactual scenarios. Extensive experiments on ActPlan-1K and ALFRED benchmarks demonstrate that LLaPa generates higher-quality plans with superior LCS and correctness, outperforming advanced models. The code and models are available https://github.com/sunshibo1234/LLaPa.
KW - counterfactual inference
KW - image segmentation
KW - procedural planning
KW - vision language models
UR - https://www.scopus.com/pages/publications/105024071924
U2 - 10.1145/3746027.3755724
DO - 10.1145/3746027.3755724
M3 - 会议稿件
AN - SCOPUS:105024071924
T3 - MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025
SP - 5020
EP - 5029
BT - MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025
PB - Association for Computing Machinery, Inc
Y2 - 27 October 2025 through 31 October 2025
ER -