Author name cluster

Biao Han

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAAI Conference 2026 Conference Paper

LLMs Unleashed: Generating Protocol Code from RFC Specifications

Junfeng Long
Jinshu Su
Biao Han

RFC (Request for Comments) documents constitute the foundation of network protocol standardization. However, they are expressed in natural language, they tend to be lengthy and ambiguous, forcing protocol implementers to rely on extensive manual parsing and coding—a process that is both labor-intensive and prone to errors. This makes the automated parsing and comprehension of RFC documents a major challenge in network protocol research. To address this gap, we introduce large language models (LLMs) into the task of automatic network protocol code generation from RFC documents (RFC2Code) and propose a comprehensive evaluation framework to quantitatively assess LLM performance. We develop an end-to-end automated protocol generation system, APG (Automated Protocol-Generation), which supports implementations of ICMP, IGMP, NTP, and TCP. Compared to prior NLP (Natural language processing) methods, APG achieves a fully automated workflow with approximately 3.17× faster processing, 95% compile success and behavioral correctness for stateless protocols like ICMP, and 90% interoperability for complex stateful protocols such as TCP, requiring only minimal manual intervention.

PDF Details DOI

YNIMG Journal 2019 Journal Article

Predictable tones elicit stimulus-specific suppression of evoked activity in auditory cortex

Biao Han
Pim Mostert
Floris P. de Lange

The auditory cortex is sensitive to many forms of acoustic regularity, resulting in suppressed neural activity for expected auditory events. It is unclear whether this activity reduction for expected events is the result of suppression of neurons that are tuned to the expected stimulus (i. e. , dampening), or alternatively suppression of neurons that are tuned away from the expected stimulus (i. e. , sharpening). In the present study, we adjudicated between these models by characterizing the effect of expectation on the ability to classify the identity of auditory stimuli from auditory neural activity patterns, using magnetoencephalography (MEG) in healthy human observers. Participants listened to pure tone pairs, in which the identity of the second tone was either expected or unexpected. The task of the participants was to detect a target tone, which deviated strongly from both the expected and unexpected tones. We found a strong suppression of the overall neural response in the expected condition compared to the unexpected condition. Linear classifiers showed a reduced ability to decode stimulus identity from event-related auditory fields in the expected condition compared to the unexpected condition. This suggests that stimulus-specific event-related activity is dampened for expected tones in auditory cortex.

Details DOI