collaborators

11 papers

cs.CL2026

StateRAG: Typed State Contracts for Complex Retrieval-Augmented Generation

Miaohe Niu, Pengxiang Li, Lianlei Shan +3

Complex retrieval-augmented generation requires evidence retrieval and control over what to retrieve next, which paths to explore, whether evidence is sufficient, and which interme…

cs.CL2026

Diffusion Language Models Know the Answer Before Decoding

Pengxiang Li, Yefan Zhou, Dilxat Muhtar +5

Diffusion language models (DLMs) have recently emerged as an alternative to autoregressive approaches, offering parallel sequence generation and flexible token orders. However, the…

cs.CV2026

Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes

Pengxiang Li, Joey Tsai, Hongwei Xue +2

Diffusion Language Models (DLMs) promise highly parallel text generation, yet their practical inference speed is often bottlenecked by suboptimal decoding schedulers. Standard appr…

cs.CL2026

Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

Pengxiang Li, Dilxat Muhtar, Tianlong Chen +2

Diffusion Language Models (DLMs) are often advertised as enabling parallel token generation, yet practical fast DLMs frequently converge to left-to-right, autoregressive (AR)-like…

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.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…