activity
20242026
collaborators

11 papers

cs.LG2026

Beyond Sparse Weights: When Is Attention Compressible?

Chiwun Yang, Xiaoyu Li

KV-cache compression is often justified by attention maps with a few large weights. This is incomplete: large weights may not contain most of the mass, omitted values can cancel, a…

cs.LG2026

RoPE Attention Can Be Trained in Almost Linear Time

Yang Cao, Jiayan Huo, Yingyu Liang +2

The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding…

cs.LG2026

On Fine-Grained I/O Complexity of Attention Backward Passes

Xiaoyu Li, Yingyu Liang, Zhenmei Shi +3

Large Language Models (LLMs) exhibit exceptional proficiency in handling extensive context windows in natural language. Nevertheless, the quadratic scaling of attention computation…

cs.DS2025

Faster Algorithm for Structured John Ellipsoid Computation

Yang Cao, Xiaoyu Li, Zhao Song +2

The famous theorem of Fritz John states that any convex body has a unique maximal volume inscribed ellipsoid, known as the John Ellipsoid. Computing the John Ellipsoid is a fundame…

cs.DS2025

Accept More, Reject Less: Reducing up to 19% Unnecessary Desk-Rejections over 11 Years of ICLR Data

Xiaoyu Li, Zhao Song, Jiahao Zhang

The explosive growth of AI research has driven paper submissions at flagship AI conferences to unprecedented levels, necessitating many venues in 2025 (e.g., CVPR, ICCV, KDD, AAAI,…

cs.LG2025

Grams: Gradient Descent with Adaptive Momentum Scaling

Yang Cao, Xiaoyu Li, Zhao Song

We introduce radient Descent with daptive omentum caling (), a novel optimization algorithm that decouples the direc…