22 citations · 55 across the 21 of their papers we have counts for
22 papers
Metis: Memory Foundation Model
Zeyu Zhang, Ziliang Guo, Yihang Sun +14
Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal foundation models and large reaso…
MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
Xixuan Hao, Zeyu Zhang, Zehao Lin +6
Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions. Existing benchmarks, however, evaluate…
SparseX: Efficient Segment-Level KV Cache Sharing for Interleaved LLM Serving
Quqing Zhang, Kai Chen, Ning Liao +5
In long-context LLM serving, the prefill stage often dominates time-to-first-token and computational cost. Although Prefix Cache in vLLM/PagedAttention has been widely used to reus…
A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
Zehao Lin, Xixuan Hao, Renyu Fu +5
The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns, ch…
TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction
Jie Zhang, Bo Tang, Wanzi Shao +8
Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which lea…
TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models
Zongzheng Zhang, Haobo Xu, Zhuo Yang +5
Many robotic manipulation tasks require sensing and responding to force signals such as torque to assess whether the task has been successfully completed and to enable closed-loop…
Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling
Ning Liao, Xiaoxing Wang, Zehao Lin +18
A large language model (LLM) with knowledge in both scientific and general tasks is the foundation of science general intelligence. However, directly continued pretraining an LLM u…
MemOS: A Memory OS for AI System
Zhiyu Li, Chenyang Xi, Chunyu Li +36
Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI), yet their lack of well-defined memory management systems hinders the…
Scalable Complexity Control Facilitates Reasoning Ability of LLMs
Liangkai Hang, Junjie Yao, Zhiwei Bai +17
The reasoning ability of large language models (LLMs) has been rapidly advancing in recent years, attracting interest in more fundamental approaches that can reliably enhance their…
MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models
Zhiyu Li, Shichao Song, Hanyu Wang +19
Large Language Models (LLMs) have emerged as foundational infrastructure in the pursuit of Artificial General Intelligence (AGI). Despite their remarkable capabilities in language…
Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations
Bo Tang, Junyi Zhu, Chenyang Xi +15
Traditional search engines struggle to synthesize fragmented information for complex queries, while generative AI search engines face challenges in relevance, comprehensiveness, an…
SurveyX: Academic Survey Automation via Large Language Models
Xun Liang, Jiawei Yang, Yezhaohui Wang +11
Large Language Models (LLMs) have demonstrated exceptional comprehension capabilities and a vast knowledge base, suggesting that LLMs can serve as efficient tools for automated sur…
FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion
Jiacheng Ruan, Yebin Yang, Zehao Lin +4
Benefiting from the revolutionary advances in large language models (LLMs) and foundational vision models, large vision-language models (LVLMs) have also made significant progress.…
MM-CamObj: A Comprehensive Multimodal Dataset for Camouflaged Object Scenarios
Jiacheng Ruan, Wenzhen Yuan, Zehao Lin +5
Large visual-language models (LVLMs) have achieved great success in multiple applications. However, they still encounter challenges in complex scenes, especially those involving ca…
: Language Modeling with Explicit Memory
Hongkang Yang, Zehao Lin, Wenjin Wang +13
The training and inference of large language models (LLMs) are together a costly process that transports knowledge from raw data to meaningful computation. Inspired by the memory h…
Similar Scenes arouse Similar Emotions: Parallel Data Augmentation for Stylized Image Captioning
Guodun Li, Yuchen Zhai, Zehao Lin +1
Stylized image captioning systems aim to generate a caption not only semantically related to a given image but also consistent with a given style description. One of the biggest ch…
Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations
Jingyao Zhou, Haipang Wu, Zehao Lin +2
Most recently proposed approaches in dialogue state tracking (DST) leverage the context and the last dialogue states to track current dialogue states, which are often slot-value pa…
MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert
Shuke Peng, Feng Ji, Zehao Lin +3
How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits t…
Predict-then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems
Zehao Lin, Shaobo Cui, Guodun Li +6
Different people have different habits of describing their intents in conversations. Some people tend to deliberate their intents in several successive utterances, i.e., they use s…
"Wait, I'm Still Talking!" Predicting the Dialogue Interaction Behavior Using Imagine-Then-Arbitrate Model
Zehao Lin, Shaobo Cui, Guodun Li +6
Producing natural and accurate responses like human beings is the ultimate goal of intelligent dialogue agents. So far, most of the past works concentrate on selecting or generatin…
Task-Oriented Conversation Generation Using Heterogeneous Memory Networks
Zehao Lin, Xinjing Huang, Feng Ji +2
How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans. To handle this problem, memory networks…
Teacher-Student Framework Enhanced Multi-domain Dialogue Generation
Shuke Peng, Xinjing Huang, Zehao Lin +3
Dialogue systems dealing with multi-domain tasks are highly required. How to record the state remains a key problem in a task-oriented dialogue system. Normally we use human-define…