From the 1 of 7 linked papers with an AI index.
7 papers
Muse: Representation Geometry of Muon Beyond Normalized Momentum
Da Chang, Qiankun Shi, Lvgang Zhang +4
The paper investigates how the choice of matrix representation influences Muon-style optimizers, proposes the Muse family of optimizers that keep the same momentum and Newton–Schul…
A Note on Stability for Orthogonalized Matrix Momentum with Client Sampling
Da Chang, Qiankun Shi, Lvgang Zhang +2
We study finite-sample generalization for a client-sampled distributed optimization scheme with matrix-valued parameters and orthogonalized momentum updates. The central quantity i…
MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration
Da Chang, Qiankun Shi, Lvgang Zhang +5
Orthogonalized-update optimizers such as Muon improve training of matrix-valued parameters, but existing extensions typically either rescale updates after orthogonalization or use…
When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression
Ruijie Zhang, Haozhe Liang, Da Chang +4
Long-context LLM inference is bottlenecked by the memory and bandwidth cost of reading large KV caches during decoding. KV compression reduces this cost by keeping only part of the…
Encoding Structural Constraints into Segment Anything Models via Probabilistic Graphical Models
Yu Li, Da Chang, Xi Xiao
While the Segment Anything Model (SAM) has achieved remarkable success in image segmentation, its direct application to medical imaging remains hindered by fundamental challenges,…
Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer
Da Chang, Yu Li
With the rapid development of OCR technology, mixed-scene text recognition has become a key technical challenge. Although deep learning models have achieved significant results in…