6 papers
REMORY: Learning Residual Memory for Context Compaction
Hanchen Xia, Baoyou Chen, Yutang Ge +5
Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent decision. We introduce REMORY, a…
ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design
Yutang Ge, Guojiang Zhao, Sihang Li +7
Designing proteins that satisfy natural language functional requirements is a central goal in protein engineering. A straightforward baseline is to fine-tune generic instruction-tu…
Latent Poincaré Shaping for Agentic Reinforcement Learning
Hanchen Xia, Baoyou Chen, Zelin Zang +3
We propose LaPha, a method for training AlphaZero-like LLM agents in a Poincaré latent space. Under LaPha, the search process can be visualized as a tree rooted at the prompt and g…
SpecXMaster Technical Report
Yutang Ge, Yaning Cui, Hanzheng Li +15
Intelligent spectroscopy serves as a pivotal element in AI-driven closed-loop scientific discovery, functioning as the critical bridge between matter structure and artificial intel…
T: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning
Hanchen Xia, Baoyou Chen, Yutang Ge +2
We present T, a simple TraceRL-based training curriculum for progressive block-size scaling in masked diffusion language models (MDMs). Starting from an AR-initialized smal…
How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliability
Yijin Zhou, Yutang Ge, Wenyuan Xie +3
Transformers excel in natural language processing and computer vision tasks. However, they still face challenges in generalizing to Out-of-Distribution (OOD) datasets, i.e. data wh…