6 citations · 8 across the 12 of their papers we have counts for
15 papers
Capability-Driven Self-Evolution of Agent Memory
Yaoqi Chen, Yuru Feng, Qianxi Zhang +8
Memory self-evolution uses task feedback to iteratively improve executable memory programs that store and retrieve information from past interactions. Existing approaches typically…
MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory
Beidi Zhao, Yaoqi Chen, Yuru Feng +10
Long-horizon agents accumulate trajectories spanning hundreds of interleaved reasoning, action, and observation steps, where answering a query may depend on evidence buried far bac…
DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System
Yizou Chen, Tsun-Yu Yang, Zhisheng Hu +2
Traditional graph processing systems are built on monolithic servers, which couple a fixed ratio of compute and memory resources but often result in resource under-utilization in d…
Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
Yaoqi Chen, Haibin Lai, Yuru Feng +12
LLM-based agents increasingly tackle long-horizon tasks with interdependent decisions, where each action reshapes future constraints and intermediate errors can cascade. Existing R…
Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
Zihan Zhao, Baotong Lu, Shengjie Lin +8
Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing only a small, query-dependent s…
KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning
Zebin Yang, Tong Xie, Baotong Lu +3
Memory-augmented Large Language Models (LLMs) have demonstrated remarkable capability for complex and long-horizon embodied planning. By keeping track of past experiences and envir…
DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation
Shuzhang Zhong, Baotong Lu, Qi Chen +3
Large language model-based deep research agents have been increasingly popular for addressing long-horizon information-seeking tasks, but they often incur high end-to-end latency d…
Scalable Distributed Vector Search via Accuracy Preserving Index Construction
Yuming Xu, Qianxi Zhang, Qi Chen +8
Scaling Approximate Nearest Neighbor Search (ANNS) to billions of vectors requires distributed indexes that balance accuracy, latency, and throughput. Yet existing index designs st…
Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study
Mocheng Li, Xiao Yan, Baotong Lu +3
With the growing integration of structured and unstructured data, new methods have emerged for performing similarity searches on vectors while honoring structured attribute constra…
Towards Efficient and Scalable Distributed Vector Search with RDMA
Xiangyu Zhi, Meng Chen, Xiao Yan +5
Similarity-based vector search facilitates many important applications such as search and recommendation but is limited by the memory capacity and bandwidth of a single machine due…
Towards Robustness: A Critique of Current Vector Database Assessments
Zikai Wang, Qianxi Zhang, Baotong Lu +2
Vector databases are critical infrastructure in AI systems, and average recall is the dominant metric for their evaluation. Both users and researchers rely on it to choose and opti…
AnTKV: Anchor Token-Aware Sub-Bit Vector Quantization for KV Cache in Large Language Models
Zeyu Li, Chuanfu Xiao, Yang Wang +6
Quantization has emerged as an effective and lightweight solution to reduce the memory footprint of the KV cache in Large Language Models. Nevertheless, minimizing the accuracy deg…
RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference
Yaoqi Chen, Jinkai Zhang, Baotong Lu +16
Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because t…
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
Di Liu, Meng Chen, Baotong Lu +11
Transformer-based Large Language Models (LLMs) have become increasingly important. However, due to the quadratic time complexity of attention computation, scaling LLMs to longer co…
SGDRC: Software-Defined Dynamic Resource Control for Concurrent DNN Inference on NVIDIA GPUs
Yongkang Zhang, Haoxuan Yu, Chenxia Han +7
Cloud service providers heavily colocate high-priority, latency-sensitive (LS), and low-priority, best-effort (BE) DNN inference services on the same GPU to improve resource utiliz…