huggingface
Score 19.8
2026-07-01 · Aryo Pradipta Gema, Beatrice Alex, Pasquale Minervini
General AI
In long-context use, large language models frequently synthesize answers from the meaning of a relevant context span rather than literally copy-pasting them. Identifying which attention heads perform this synthesis matters for interpreting long-context model behavior. Yet existing detectors miss these heads by construc…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 19.0
2026-06-29 · Peyman Hosseini, Ondrej Bohdal, Ahmed Alajrami, Andrea Maracani, Ignacio Castro, Matthew Purver, Mete Ozay, Savas Ozkan, Taha Ceritli
General AI
Large Language Model (LLM)-based agents can solve complex procedural tasks by interacting with environments over multiple turns, but this ability typically depends on large models, long contexts, and repeated inference calls. This makes advanced memory-augmented agents difficult to deploy on resource-constrained device…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 11.9
2026-06-26 · Kuo-Chung Peng, Jiun-Cheng Jiang, Chun-Hua Lin, Tai-Yue Li, Nan-Yow Chen, Samuel Yen-Chi Chen
General AI
Traffic matrices (TMs) capture network-wide origin-destination demand and are central to traffic engineering, yet accurate whole-matrix forecasting remains challenging when prediction must be performed under the memory, update, and training-budget constraints of online network control. This paper investigates whether c…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 10.8
2026-07-01 · Shengguang Wu, Hao Zhu, Yuhui Zhang, Xiaohan Wang, Serena Yeung-Levy
General AI
Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capacity known in cognitive science as metamemory. We bring this perspective to LLMs by treating memory management as a trainable skill. We promote file-system operations to first-class memory actions alongsi…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 8.8
2026-07-02 · Haiyang Li, Yuming Fu, Qun Song, Hongchao Liao, Jing Chen, Mounim A. EI-Yacoubi, Xin Jin
General AI
Vein recognition is a secure biometric technology often constrained by limited annotated data and imaging variations. While data augmentation mitigates this, strategies designed for natural images may disrupt the fine-grained topology and textures essential for identity discrimination. We present AGVBench, which evalua…
- Review
- pending
- Role
- unreviewed
- Read
- soon