4 papers
CPUNeSy: Controlling Model Writes for Reliable Neuro-Symbolic Reasoning
Zeyan Li, Siyuan Qiu, Shuai Zhao +1
LLMs excel at recalling statistical patterns but degrade sharply when answers must be derived, especially on multi-hop chains. Delegating derivation to deterministic symbolic execu…
SemRD-V2X: Closure-Guided Communication with Bounded Inference for Cooperative Perception
Hu Xu, Chun Li, Siyuan Qiu +2
Vehicle-to-Everything (V2X) cooperative perception improves 3-D detection by sharing intermediate features, but dense remote features may repeat context that the ego agent can infe…
Regime Boundary Alignment for Evidence-Gated Question Answering
Zeyan Li, Qirong Guo, SIyuan Qiu +3
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 behav…
Reasoning Instructions Can Break Answer Decoding in Vision--Language Models
Zeyan Li, Siyuan Qiu, Jianfeng Xu
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 ra…