Harbin Engineering University

Multivariate time-series anomaly detection has long relied on graph detectors trained from scratch on limited target-domain data, whose learned sensor topologies are prone to spurious correlations and cannot reuse relational priors from pretrained graph models. Gfm4Mtsad wraps a frozen graph foundation model in three peripheral modules: SICA aligns temporal features with normal-connectivity priors and restores projection-lost detail, MAPS synthesizes near-boundary pseudo-anomalies through residual-preserving local dependency breaks, and TGEC re-ranks multi-granular evidence only in the upper score tail. Across MSL P-15, SMAP T-3 and SMD 1-1 with AnomalyGFM and OwlEye backbones, the adaptation reaches best or second-best results on most metrics.

Multivariate time-series anomaly detection has long relied on graph detectors trained from scratch on limited target-domain data, whose learned sensor topologies are prone to spurious correlations and cannot reuse relational priors from pretrained graph models. Gfm4Mtsad wraps a frozen graph foundation model in three peripheral modules: SICA aligns temporal features with normal-connectivity priors and restores projection-lost detail, MAPS synthesizes near-boundary pseudo-anomalies through residual-preserving local dependency breaks, and TGEC re-ranks multi-granular evidence only in the upper score tail. Across MSL P-15, SMAP T-3 and SMD 1-1 with AnomalyGFM and OwlEye backbones, the adaptation reaches best or second-best results on most metrics.

Single-frame fringe pattern analysis in digital holographic interferometry has relied on manually set Fourier-domain filter windows, which are hard to choose when noise, defocus or overexposure degrade the fringes. An adaptive spectrum filtering network turns Fourier-domain filtering into learnable attention weights that select +1st-order spectral content per input, and is trained on forward-model simulations with added noise and overexposure. On 400 simulated test samples it beats tuned Fourier-transform analysis and an end-to-end ResUNet in pixel error, and after simulation-only training it produces fewer artifacts and outliers than hand-tuned Fourier analysis on unseen experimental interferograms.

Single-frame fringe pattern analysis in digital holographic interferometry has relied on manually set Fourier-domain filter windows, which are hard to choose when noise, defocus or overexposure degrade the fringes. An adaptive spectrum filtering network turns Fourier-domain filtering into learnable attention weights that select +1st-order spectral content per input, and is trained on forward-model simulations with added noise and overexposure. On 400 simulated test samples it beats tuned Fourier-transform analysis and an end-to-end ResUNet in pixel error, and after simulation-only training it produces fewer artifacts and outliers than hand-tuned Fourier analysis on unseen experimental interferograms.

The authors propose Residual Advantage (RA), which treats the teacher–student probability residual as a bounded one-step reward, subtracts the corresponding state value under the student policy to form an advantage, and centers it within each response before adding it to the verifier advantage, so the verifier sets a response's mean label while the teacher only redistributes credit among its steps; with Qwen3-1.7B/4B-Base students and a Qwen3-8B teacher, RA combined with GRPO or REINFORCE++ improves all 24 three-seed comparisons on three mathematical benchmarks, raising macro Avg@8 by 1.7–3.6 points and Pass@8 by 3.9–6.3 points, surpassing teacher-only OPD; Co-RA updates a teacher LoRA with verifier advantages on the same scored student batch and adds a further 1.0–1.5 Avg@8 points.

The authors propose Residual Advantage (RA), which treats the teacher–student probability residual as a bounded one-step reward, subtracts the corresponding state value under the student policy to form an advantage, and centers it within each response before adding it to the verifier advantage, so the verifier sets a response's mean label while the teacher only redistributes credit among its steps; with Qwen3-1.7B/4B-Base students and a Qwen3-8B teacher, RA combined with GRPO or REINFORCE++ improves all 24 three-seed comparisons on three mathematical benchmarks, raising macro Avg@8 by 1.7–3.6 points and Pass@8 by 3.9–6.3 points, surpassing teacher-only OPD; Co-RA updates a teacher LoRA with verifier advantages on the same scored student batch and adds a further 1.0–1.5 Avg@8 points.