AAAI

Towards Human-AI Accessibility Mapping in India: VLM-Guided Annotations and POI-Centric Analysis in Chandigarh

迈向印度的人机可及性映射：在昌迪加尔的VLM引导标注与POI中心分析

Varchita Lalwani, Utkarsh Agarwal, Michael Saugstad, Manish Kumar, Jon E. Froehlich, Anupam Sobti

AI总结 本文提出在印度昌迪加尔部署Project Sidewalk工具，通过VLM引导标注和POI中心分析，评估了城市无障碍性改进的潜力。

Comments Accepted at the Second Workshop on AI for Urban Planning (AI4UP) at AAAI 2026

Bridging Day and Night: Target-Class Hallucination Suppression in Unpaired Image Translation

弥合昼夜：无配对图像翻译中的目标类幻觉抑制

Shuwei Li, Lei Tan, Robby T. Tan

AI总结 本文提出了一种新型框架，通过双头判别器和类特定原型抑制无配对图像翻译中的目标类幻觉，提升翻译质量与下游任务性能。

Comments Accepted at AAAI 2026 (Oral)

Sparse Additive Model Pruning for Order-Based Causal Structure Learning

基于顺序因果结构学习的稀疏加法模型剪枝

Kentaro Kanamori, Hirofumi Suzuki, Takuya Takagi

AI总结 本文提出基于稀疏加法模型的因果结构学习剪枝方法，通过高效算法提升剪枝效率并保持高准确性。

Comments 15 pages, 12 figures, to appear in the 40th AAAI Conference on Artificial Intelligence (AAAI 2026)

Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces

超越事实检索：具有生成语义工作区的RAG episodic记忆

Shreyas Rajesh, Pavan Holur, Chenda Duan, David Chong, Vwani Roychowdhury

AI总结 GSW通过生成语义工作区提升LLM的长上下文推理能力，实现更高效的记忆管理与时空连贯性。

Comments AAAI 2026 Oral, code available at: https://github.com/roychowdhuryresearch/gsw-memory