Skip to content

Author

Si-Yuan Qiu

6 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

CPUNeSy: Controlling Model Writes for Reliable Neuro-Symbolic Reasoning

CPUNeSy, a serving architecture that controls model writes to symbolic state via a task-defined predicate interface and certificate gate, abstaining when grounding passes disagree is introduced, showing deterministic execution drives most accuracy recovery on derivation-heavy tasks.

Zeyan Li, Si-Yuan Qiu, Shuai Zhao et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Regime Boundary Alignment for Evidence-Gated Question Answering

Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence is missing. We trace this behavior to the training signal: answer-focused fine-tuning assigns no target to unsupported contexts, so it cannot distinguish a reader that abs...

Zeyan Li, Qi-Rong Guo, Si-Yuan Qiu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

SemRD-V2X: Closure-Guided Communication with Bounded Inference for Cooperative Perception

SemRD-V2X is an operational neural proxy that combines exact-budget BEV support selection, pointwise channel compression, and masked shared-weight reconstruction before standard fusion before standard fusion, and position closure fidelity as both an analytical lens and an actionable design principle for communication-e...

Hu Xu, Chun Li, Si-Yuan Qiu et al. · 0 citations
#machine learning Preprint Sep 2026

New LoRA Skills Should Read but Never Write

Low-rank adapters (LoRA) make it cheap to fine-tune a large language model once per task, but combining several independently trained adapters into one model remains difficult: merging the updates in weight space causes interference, retraining on all task data is expensive, and routing between separate adapters gives...

Zeyan Li, Pan-Qi Yang, Qi-Rong Guo et al. · 0 citations

Reasoning Instructions Can Break Answer Decoding in Vision-Language Models

Chain-of-thought (CoT) instructions can distort multiple-choice VLM evaluation when a scorer appends a reasoning cue but reads answer-label logits before the model generates any rationale. We call this CoT-prefix scoring. On ScienceQA, Qwen2.5-VL-7B drops from 80.76% to 45.48%, and across five option-content permutatio...

Zeyan Li, Si-Yuan Qiu, Jian-Feng Xu · 0 citations
#federated learning Review Open access Sep 2026

Artificial Intelligence-Enabled Low-Carbon Transition in Shipping: A Systematic Bibliometric Review

An evidence-informed AI-to-Carbon Value Chain conceptual synthesis comprising data observability, model credibility, decision executability, system coordination, and carbon verification is advanced, although this synthesis is interpretive rather than a validated causal framework.

Xiao-Yang Liu, Chuan-Xu Wang, Ming Yin et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.