3 papers
cs.CL2026
Learning What to Remember: Test-Time Training via Context Distillation
Zixuan Wang, Xingyu Dang, Rui-Jie Zhu +4
Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later. Test-time training (TTT) is an a…
cs.CL2026
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
Hengyu Fu, Tianyu Guo, Zixuan Wang +5
Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT). However, many questions require t…
cs.CL2025
Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding
Jiajun Zhu, Peihao Wang, Ruisi Cai +3
Transformers rely on both content-based and position-based addressing mechanisms to make predictions, but existing positional encoding techniques often diminish the effectiveness o…