1 citations · 1 across the 7 of their papers we have counts for
6 papers · 1 filter
Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts
Di He, Pengxiang Li, Da Chang +3
Looped Transformers introduce recurrent depth as a new scaling axis for LLMs: by repeatedly applying shared Transformer blocks, they increase effective depth without increasing par…
Muse: Representation Geometry of Muon Beyond Normalized Momentum
Da Chang, Qiankun Shi, Lvgang Zhang +4
Muon-style optimizers apply a polar map to matrix momentum, but their updates also depend on the representation of each parameter block before orthogonalization. We study this repr…
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…
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…
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…
AlphaAdam:Asynchronous Masked Optimization with Dynamic Alpha for Selective Updates
Da Chang, Yu Li, Ganzhao Yuan
In the training of large language models (LLMs), updating parameters more efficiently and stably has always been an important challenge. To achieve efficient parameter updates, exi…