Searcharxiv⌕ Search

arXiv subjects

Yiliu Xu

Publications and source records attributed to Yiliu Xu.

6 recordsLinked to original sources

AITHER: Authority-Informed Evidence Routing for Mixed-Authority Vision-Language Reasoning

Reliable vision-language reasoning requires a control decision that conventional grounding methods leave implicit: which input is entitled to determine the answer? Auxiliary text may be a defeasible claim about an image, a binding task instruction, or compatible context. Correcting every image-text conflict toward the image therefore repairs false claims but overwrites valid task rules. We formalize this setting as mixed-authority vision-language reasoning and introduce AITHER, an Authority-Informed Text-Image Hierarchy for Evidence Routing. Its final policy, the Semantic-Frame Router, is a training-free black-box control layer that (i) compiles explicit task directives, (ii) recovers standardized spatial frames from metadata-scrubbed pixels, (iii) resolves the semantic polarity of remaining notes, and (iv) routes among frozen observable candidates with fail-closed semantics. This ordered decomposition converts authority arbitration from an unconstrained prompt preference into a reproducible inference program. Across 1,620 MATRIX predictions, AITHER reaches 95.1% accuracy, exceeding the strongest task-and-frame baseline by 9.1 points with a 95% record-cluster interval of 6.8-11.5 points and no harmed records. It further reaches 100.0% on 1,800 controlled FRAME predictions and 93.3% on GQA-MATRIX. The results show that explicit authority routing can simultaneously improve false-claim correction, preserve task-defined answers, and eliminate clean-context overcorrection.

cs.CV↗

What Breaks in Multi-Image Schema Application? Factorial Oracle Interventions Reveal an Instance-Information Bottleneck

Modern vision-language models can accept multi-image contexts, but aggregate accuracy rarely reveals where a multi-image reasoning pipeline fails. We study a controlled schema-application task in which a model must locate two target characters in a 16-image sequence, identify their visual attributes, consult an item-specific visual codebook, and compose two ordered nonce code names. We introduce a within-item 2-by-2 factorial Oracle design: Oracle-A supplies a verified textual schema, Oracle-B supplies a verified ordered target-appearance representation, and both interventions retain the original images and final question. Across 72 new items and 1,188 analyzed model responses, Oracle-B increased strict exact accuracy by 54.6 percentage points (95% confidence interval: 46.3 to 63.0) and outperformed Oracle-A by 60.6 points (Holm-adjusted p-value no greater than .0002). An auxiliary retrieval diagnostic reached only 49.1% ordered-appearance accuracy even after removing code-name generation. Providing both Oracle sources yielded 100% accuracy across all models. These results localize the dominant recoverable deficit to upstream ordered instance recovery rather than primarily to downstream schema use and composition.

cs.CV↗

GeoCueFormer: Geometry-Guided Wavelet Representation and Prediction-Cued Dual-Stage Decoder for Underwater Semantic Segmentation

Underwater semantic segmentation is essential for marine ecosystem monitoring, yet remains challenging due to severe visual degradation. Light absorption and scattering often lead to color shifts, low contrast, and blurred boundaries, making shallow detail features unreliable. Existing underwater segmentation methods improve RGB feature aggregation or boundary prediction, but still lack an explicit mechanism to distinguish structure-related details from degradation-induced responses. To address this limitation, we propose GeoCueFormer, a lightweight framework that combines geometry-constrained frequency enhancement with prediction-cued refinement. GeoCueFormer performs stage-specific wavelet enhancement on hierarchical encoder features to complement shallow boundary details while preserving deep structural semantics. A depth-derived spatial gate constrains shallow frequency enhancement toward geometry-consistent regions, and a prediction-cued dual-stage decoder further refines ambiguous high-resolution features. GeoCueFormer obtains 82.23% and 73.04% mIoU on SUIM and DUT, respectively. Under comparable model complexity and standard benchmark settings on SUIM and DUT, it achieves SOTA performance while maintaining a favorable accuracy-complexity trade-off. These results show that distinguishing structural details from degradation-induced interference is more effective for underwater segmentation.

cs.CV↗

GRACE: Grounded Reasoning via Adapter Composition and Evidence-Aware Calibration for Educational Visual Question Answering

Educational visual question answering, or VQA, requires models to solve curriculum-oriented multiple-choice questions using both language and visual evidence. Compared with conventional open-ended VQA, educational examples often include structured assessment metadata, diagrams or image contexts, and semantically close answer options, creating strong opportunities for question-option shortcuts. We develop and evaluate a parameter-efficient adaptation framework for a frozen multimodal large language model in this setting. We introduce GRACE, Grounded Reasoning via Adapter Composition and Evidence-Aware Calibration, a framework that uses the pedagogical state of each question to specialize lightweight language and vision adaptation. The state combines inference-visible subject, grouped skill, grade, visual-context, question-intent, and option-structure cues. GRACE uses factor-specific prompts and lightweight visual adapters, then applies evidence-aware option calibration to score all candidates under a shared multimodal context. On ScienceQA, GRACE improves a shared-adapter baseline from 90.5 percent to 93.1 percent overall accuracy and from 88.7 percent to 91.2 percent on image-context questions. Removing pedagogical composition, option calibration, or the visual adapter reduces overall accuracy by 1.4, 1.0, and 1.5 points, respectively. These controlled results show that structured educational state is an effective routing signal for parameter-efficient multimodal adaptation.

cs.MM↗

Chain-Aware Encoding for Microservice Trace Anomaly Detection

Microservice traces can be structurally anomalous even when every span returns normally -- a payment flow that silently skips a risk check looks fine to any per-span monitor. Sequence models like DeepLog address this by predicting the next event, but they treat each API endpoint as a context-free token: the same endpoint reached through different invocation chains is mapped to the same vocabulary entry, even when its normal behavior differs across contexts. We propose encoding each event as an (endpoint, root-to-span invocation chain) pair instead. This simple change has two consequences: unseen chains are flagged without model inference, and next-event predictions become context-conditional, turning subtle path anomalies into clear outliers. We instantiate this idea in CHAINLSTM, a lightweight dual-task LSTM supporting per-event online detection. On the TrainTicket benchmark, CHAINLSTM achieves 94.3% F1 (+5.3 pp over DeepLog) with comparable latency recall and 99.1\% path recall. Case analysis shows that chain-aware encoding shifts median prediction probability on path anomalies from 0.91 to 0.002, suggesting a wider separation margin for threshold-based detection.

cs.SE↗

Signal identification with Kalman Filter towards background-free neutrinoless double beta decay searches in gaseous detectors

Particle tracks and differential energy loss measured in high pressure gaseous detectors can be exploited for event identification in neutrinoless double beta decay~($0νββ$) searches. We develop a new method based on Kalman Filter in a Bayesian formalism (KFB) to reconstruct meandering tracks of MeV-scale electrons. With simulation data, we compare the signal and background discrimination power of the KFB method assuming different detector granularities and energy resolutions. Typical background from $^{232}$Th and $^{238}$U decay chains can be suppressed by another order of magnitude than that in published literatures, approaching the background-free regime. For the proposed PandaX-III experiment, the $0νββ$ search half-life sensitivity at the 90\% confidence level would reach $2.7 \times 10^{26}$~yr with 5-year live time, a factor of 2.7 improvement over the initial design target.

physics.ins-det↗