https://deep-learning-profiling-tools.github.io/CAT-Lab/tag/aacl/AACLHugo Blox Builder (https://hugoblox.com)en-usTue, 08 Sep 2026 00:00:00 +0000https://deep-learning-profiling-tools.github.io/CAT-Lab/media/icon_hu6808975029018430273.pnghttps://deep-learning-profiling-tools.github.io/CAT-Lab/tag/aacl/https://deep-learning-profiling-tools.github.io/CAT-Lab/news/2026-09-08-automem-aacl2026/Tue, 08 Sep 2026 00:00:00 +0000https://deep-learning-profiling-tools.github.io/CAT-Lab/news/2026-09-08-automem-aacl2026/<p>Our collaborative paper <a href="https://deep-learning-profiling-tools.github.io/CAT-Lab/CAT-Lab/publication/automem_aacl2026/"><em>Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline</em></a>, by <strong>Zhikai Chen, Jialiang Gu, Junyu Yin, Xianxuan Long, Shenglai Zeng, Xiaoze Liu, Kai Guo, Keren Zhou, and Jiliang Tang</strong>, has been accepted at <strong>AACL-IJCNLP 2026</strong>. The paper evaluates agent memory systems across different scenarios and introduces AutoMEM, a baseline that lets agents manage memory through tools. Congratulations to all the authors!</p>https://deep-learning-profiling-tools.github.io/CAT-Lab/news/2026-09-08-tilebench-aacl2026/Tue, 08 Sep 2026 00:00:00 +0000https://deep-learning-profiling-tools.github.io/CAT-Lab/news/2026-09-08-tilebench-aacl2026/<p>Our paper <a href="https://deep-learning-profiling-tools.github.io/CAT-Lab/CAT-Lab/publication/tilebench_aacl2026/"><em>TileBench: A Controlled Benchmark for Performance Evaluation and Bottleneck Diagnosis of Tile-Based Programming Models</em></a>, by <strong>Bowen Cui, Zhongchun Zhou, Hao Wu, Tejas Ramesh, Junyu Yin, Jialiang Gu, and Keren Zhou</strong>, has been accepted at <strong>AACL-IJCNLP 2026</strong>. TileBench compares tile-based GPU programming models under controlled conditions and supports profiling-guided diagnosis of performance bottlenecks. Congratulations to all the authors!</p>