mlsanityData to 14 Oct 2026

HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting

arXiv 2608.11692 ↗First posted 12 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous logistics sorting systems (ALSS) are an important industrial application of embodied AI, which requires joint planning over spatially disjoint camera views. We formulate this setting as Joint Multi-Scene Understanding (JMSU). With open-world visual understanding and task-planning capabilities, vision-language models (VLMs) are promising candidates for JMSU. However, directly applying existing VLMs to JMSU is non-trivial due to scarce cross-scene supervision and attention dispersion caused by long visual context in JMSU. To address these challenges, we propose HUGIN, a training framework with two complementary components. Endogenous Data Augmentation recombines verified atomic facts under operating constraints, while Global Context Ranking aligns the instruction representation more strongly with the complete visual context than with a partial visual context. To support ongoing research, we construct a high-quality industrial sorting dataset and benchmark named SortingBench from four layouts of autonomous logistics sorting systems. Across five open VLMs, HUGIN consistently outperforms matched baselines; for example, the accuracy on SortingBench of Qwen3-VL-8B increases from 63.6% to 78.8%. Additional experiments verify the effectiveness of each component and JMSU's spillover benefits in embodied tasks. Deployment tests involving more than 15,000 packages support the practical viability of VLM-based planning for autonomous logistics sorting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 12 Aug 2026.

Builds on

29 of 41 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  5. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  6. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  7. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  8. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  9. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 572
  10. 2024VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Modelscited by 455
  11. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
  12. 2023In-Context Learning Creates Task Vectorscited by 312
17 more
  1. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 215
  2. 2025VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interactioncited by 197
  3. 2025MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipecited by 186
  4. 2023SVIT: Scaling up Visual Instruction Tuningcited by 162
  5. 2025RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concretecited by 135
  6. 2023Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselvescited by 123
  7. 2023The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open Worldcited by 116
  8. 2023The geometry of hidden representations of large transformer modelscited by 112
  9. 2025Ovis2.5 Technical Reportcited by 108
  10. 2024The All-Seeing Project V2: Towards General Relation Comprehension of the Open Worldcited by 90
  11. 2023VeCLIP: Improving CLIP Training via Visual-enriched Captionscited by 70
  12. 2024Aligning Large Language Models with Representation Editing: A Control Perspectivecited by 64
  13. 2025Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenescited by 63
  14. 2026RoboBrain 2.5: Depth in Sight, Time in Mindcited by 39
  15. 2025RationalVLA: A Rational Vision-Language-Action Model with Dual Systemcited by 12
  16. 2025HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMscited by 9
  17. 2024VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Modelscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025TinyGiantVLM: A Lightweight Vision-Language Architecture for Spatial Reasoning under Resource Constraints
  2. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
  3. 2025Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes
  4. 2024VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs
  5. 2025VLMPlanner: Integrating Visual Language Models with Motion Planning
  6. 2025ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models
  7. 2026Grounding Vision and Language to 3D Masks for Long-Horizon Box Rearrangement
  8. 2026Plan-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds?