5 papers
Demystifying Data Organization for Enhanced LLM Training
Yalun Dai, Yangyu Huang, Tongshen Yang +8
Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation. While data selection has been widely s…
MoleCode unlocks structural intelligence in large language models
Zhiyuan Yan, Chen Liu, Boxuan Zhao +8
Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular representation, SMILES, compresses…
CASTLE: Contrastive and Seed-Guided Training for Cold-Start Natural Language Search
Wendy Ran Wei, Hao Li, Weiwei Guo +9
Deploying natural language search systems presents a critical cold-start challenge: no real user queries to learn linguistic patterns, and no relevance labels to train ranking mode…
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…