4 papers
Jacap: Robust KV Cache Eviction via Jacobian-Based Nonlinear Information Capacity Preservation
Jiaming Yang, Chenwei Tang, Liangli Zhen +2
Key-value (KV) cache eviction is essential for scaling long-context inference in Large Language Models. However, existing policies predominantly rely on empirical heuristics, lacki…
Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
Jiaming Yang, Chenwei Tang, Liangli Zhen +1
Key-Value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generation. Existing eviction policies…
SAG-Agent: Enabling Long-Horizon Reasoning in Strategy Games via Dynamic Knowledge Graphs
Chenwei Tang, Lin Long, Xinyu Liu +6
Most commodity software lacks accessible Application Programming Interfaces (APIs), requiring autonomous agents to interact solely through pixel-based Graphical User Interfaces (GU…
Memory-Augmented Dual-Decoder Networks for Multi-Class Unsupervised Anomaly Detection
Jingyu Xing, Chenwei Tang, Tao Wang +5
Recent advances in unsupervised anomaly detection (UAD) have shifted from single-class to multi-class scenarios. In such complex contexts, the increasing pattern diversity has brou…