Tong Chen

Revela: Dense Retriever Learning via Language Modeling

Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval

Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations

Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data