5 papers · 1 filter
On the Position Bias of On-Policy Distillation
Yan Xie, Sijie Zhu, Tiansheng Wen +2
On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers. In the standard KL objective…
Scaling Attention via Feature Sparsity
Yan Xie, Tiansheng Wen, Tangda Huang +4
Scaling Transformers to ultra-long contexts is bottlenecked by the cost of self-attention. Existing methods reduce this cost along the sequence axis through local window…
Route Experts by Sequence, not by Token
Tiansheng Wen, Yifei Wang, Aosong Feng +7
Mixture-of-Experts (MoE) architectures scale large language models (LLMs) by activating only a subset of experts per token, but the standard TopK routing assigns the same fixed num…
CSRv2: Unlocking Ultra-Sparse Embeddings
Lixuan Guo, Yifei Wang, Tiansheng Wen +5
In the era of large foundation models, the quality of embeddings has become a central determinant of downstream task performance and overall system capability. Yet widely used dens…
Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
Tiansheng Wen, Yifei Wang, Zequn Zeng +7
Many large-scale systems rely on high-quality deep representations (embeddings) to facilitate tasks like retrieval, search, and generative modeling. Matryoshka Representation Learn…