3 papers
cs.LG2026
When Does Embedding Magnitude Matter? A Cross-Task Functional-Symmetry Framework
Xincan Feng, Taro Watanabe
Cosine similarity normalizes both sides; dot product normalizes neither. We propose a 2x2 framework that independently controls query-side and document-side normalization, exposing…
cs.LG2025
SeqPE: Transformer with Sequential Position Encoding
Huayang Li, Yahui Liu, Hongyu Sun +5
Since self-attention layers in Transformers are permutation invariant by design, positional encodings must be explicitly incorporated to enable spatial understanding. However, fixe…
cs.CL2024
ALR: A Retrieve-then-Reason Framework for Long-context Question Answering
Huayang Li, Pat Verga, Priyanka Sen +5
The context window of large language models (LLMs) has been extended significantly in recent years. However, while the context length that the LLM can process has grown, the capabi…