5 papers
Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training
Kailai Yang, Xiao Liu, Lei Ji +6
Continual pre-training on small-scale task-specific data is an effective method for improving large language models in new target fields, yet it risks catastrophic forgetting of th…
MemAdapter: Fast Alignment across Agent Memory Paradigms via Generative Subgraph Retrieval
Xin Zhang, Kailai Yang, Chenyue Li +4
Memory mechanism is a core component of LLM-based agents, enabling reasoning and knowledge discovery over long-horizon contexts. Existing agent memory systems are typically designe…
Implicit Graph, Explicit Retrieval: Towards Efficient and Interpretable Long-horizon Memory for Large Language Models
Xin Zhang, Kailai Yang, Hao Li +3
Long-horizon applications increasingly require large language models (LLMs) to answer queries when relevant evidence is sparse and dispersed across very long contexts. Existing mem…
MIRA: Medical Time Series Foundation Model for Real-World Health Data
Hao Li, Bowen Deng, Chang Xu +8
A unified foundation model for medical time series -- pretrained on open access and ethics board-approved medical corpora -- offers the potential to reduce annotation burdens, mini…
Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement
Hao Li, Yizheng Sun, Viktor Schlegel +3
Argument summarization aims to generate concise, structured representations of complex, multi-perspective debates. While recent work has advanced the identification and clustering…