collaborators

7 papers

cs.LG2026

ISO: An RLVR-Native Optimization Stack

Hanqing Zhu, Wenyan Cong, Zhizhou Sha +8

Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language models, yet the optimization layer that converts reward feedback i…

cs.CL2026

When Does Sparsity Mitigate the Curse of Depth in LLMs

Dilxat Muhtar, Xinyuan Song, Sebastian Pokutta +4

Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation than earlier layers. Such under-u…

cs.SD2026

AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling

Jiacheng Shi, Hongfei Du, Xinyuan Song +3

Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acousti…

cs.LG2026

The Curse of Depth in Large Language Models

Wenfang Sun, Xinyuan Song, Pengxiang Li +3

In this paper, we introduce the Curse of Depth, a concept that highlights, explains, and addresses the recent observation in modern Large Language Models (LLMs) where nearly half o…

cs.CL2026

ActTail: Global Activation Sparsity in Large Language Models

Wenwen Hou, Xinyuan Song, Shiwei Liu

Activation sparsity is a promising approach for accelerating large language model (LLM) inference by reducing computation and memory movement. However, existing activation sparsity…

cs.AI2026

Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning

Xinyuan Song, Keyu Wang, PengXiang Li +2

Recent studies suggest that the deeper layers of Large Language Models (LLMs) contribute little to representation learning and can often be removed without significant performance…