3 citations · 3 across the 16 of their papers we have counts for
19 papers
To Keep or Not to Keep: Learning KV Cache Retention in Disaggregated LLM Serving Systems
Dong Liu, Yanxuan Yu, Eric Jiang +2
Disaggregated \textsc{LLM} serving separates prefill and decode across node pools, placing a network fabric between \textsc{KV}-cache computation and consumption. This breaks a key…
MeshKV: A Network-on-Chip KV Cache Fabric for Scalable Transformer Decoding Accelerators
Dong Liu, Yanxuan Yu
Autoregressive transformer decoding is constrained by irregular key-value (KV) cache movement on tiled accelerators. Prior compression and DRAM-placement systems still concentrate…
RUBRIC: Realism--Utility Balanced Ranking for Imbalanced Classification
Yanxuan Yu, Dong Liu, Shu Wang +9
Class imbalance poses a fundamental challenge in risk-sensitive applications such as fraud detection and medical diagnosis, where minority-class samples are scarce yet critical for…
HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers
Dong Liu, Yanxuan Yu, Renata Borovica-Gajic +2
Vision transformers face significant computational overheads in high-resolution dense prediction due to the quadratic complexity of self-attention. Linear attention offers efficien…
Context-Adaptive Inference: A Unified Statistical and Foundation-Model View
Yue Yao, Caleb N. Ellington, Jingyun Jia +9
Modern predictive systems are expected to adapt their behavior to the specific situation they are facing. A clinical model should not treat every patient the same; a retrieval-augm…
OLIVE: Online Low-Rank Incremental Learning for Efficient Adaptive Exoskeletons
Dong Liu, Yanxuan Yu, Ben Lengerich +2
Wearable exoskeleton systems hold promise for restoring mobility in individuals with physical impairments, yet most existing controllers rely on static gait policies that cannot ad…
Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching
Dong Liu, Yanxuan Yu, Ying Nian Wu
Diffusion models achieve remarkable success in time series generation. However, slow inference limits their practical deployment. We propose E-CRF (Error-Feedback Event-Driven…
The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
Chen Qian, Peng Wang, Dongrui Liu +10
Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more…
AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers
Dong Liu, Yanxuan Yu, Ben Lengerich +1
Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising…
INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems
Yijin Zhou, Xiaoya Lu, Dongrui Liu +2
The rapid advancement of Large Language Model (LLM)-based Multi-Agent Systems (MAS) has introduced significant security vulnerabilities, where malicious influence can propagate vir…
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Dongrui Liu, Qihan Ren, Chen Qian +40
The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk…
Are Your Agents Upward Deceivers?
Dadi Guo, Qingyu Liu, Dongrui Liu +13
Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in…
CSV-Decode: Certifiable Sub-Vocabulary Decoding for Efficient Large Language Model Inference
Dong Liu, Shu Wang, Yanxuan Yu +2
Large language models face significant computational bottlenecks during inference due to the expensive output layer computation over large vocabularies. We present CSV-Decode, a no…
SPI: Query-Depth-Adaptive Indexing for Streaming RAG in Vector Databases
Dong Liu, Yanxuan Yu
Vector databases (VecDBs) are increasingly deployed in retrieval-augmented generation (RAG) pipelines where query processing and document ingestion occur concurrently. The index la…
ConEQsA: Concurrent and Asynchronous Embodied Questions Scheduling and Answering
Haisheng Wang, Dong Liu, Weiming Zhi
This paper formulates the Embodied Questions Answering (EQsA) problem, introduces a corresponding benchmark, and proposes an agentic system to tackle the problem. Classical Embodie…
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
Huan-ang Gao, Jiayi Geng, Wenyue Hua +24
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks but remain fundamentally static, unable to adapt their internal parameters to novel task…
Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
Jiahao Qiu, Xuan Qi, Tongcheng Zhang +15
Recent advances in large language models (LLMs) have enabled agents to autonomously perform complex, open-ended tasks. However, many existing frameworks depend heavily on manually…
Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models
Yifan Jia, Kailin Jiang, Yuyang Liang +11
Large Multimodal Models(LMMs) face notable challenges when encountering multimodal knowledge conflicts, particularly under retrieval-augmented generation(RAG) frameworks where the…
Evaluating the Correctness of Inference Patterns Used by LLMs for Judgment
Lu Chen, Yuxuan Huang, Yixing Li +6
This paper presents a method to analyze the inference patterns used by Large Language Models (LLMs) for judgment in a case study on legal LLMs, so as to identify potential incorrec…