4 papers
Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection
Yan Zhan, Yunze Song, Mengkai Hou +3
Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template marker such as <|im_start|> c…
Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning
Yan Zhan, Shaobo Liu, Zhijun Gao
Discrete diffusion language models (dLLMs) expose a denoised solution at every step, which makes process reward model (PRM) guidance look like a way to spend compute at test time.…
Length-Adaptive Decoding for Masked Diffusion Machine Translation
Yan Zhan, Mengkai Hou, Wanting Zhang +1
Machine translation tests masked diffusion language models (dLLMs) because every source token must be rendered faithfully, while fixed canvas decoding must choose target length bef…
From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation
Zhijun Gao, Jing Chen
Technical documentation is written for human developers, but an increasing share of software changes is now authored by autonomous coding agents. Which documents they consult, when…