A new arxiv preprint proposes swapping self-attention for phase-shifts and a Fourier transform, cutting parameters by orders of magnitude on synthetic time-series.
TimeAPN is a plug-in normalization layer that models amplitude and phase shifts in the frequency domain, boosting long-horizon forecasts across four backbones.
Alibaba's Baguan-TS introduces a 3D Transformer that unifies raw-sequence learning with in-context adaptation, beating Chronos, TimesFM and TabPFN-TS on covariate-aware forecasting.
A new transformer framework treats cross-attention as domain translation, injects Gaussian noise into keys and values, and adds multi-scale matching to close domain gaps.
A new vision-language-action framework decouples task goals from motion details, letting robots follow fine-grained kinematic instructions like orientation, direction, and trajectory.
A new federated learning recipe uses pre-trained weights to shrink client uplink traffic by roughly 80 percent while keeping accuracy on par with uncompressed baselines.
AirDDE is the first neural delay differential equation for air quality, treating pollutant transport as a delayed physical process and cutting MAE by 8.79%.
A single frozen backbone plays both teacher and student, cutting memory by up to 149x while matching state-of-the-art anomaly detection on MVTec and VisA.
A training-free method animates 4K frescos by using a low-resolution video as a global prior to guide tiled denoising, preserving both fine detail and scene-wide coherence.
A new framework builds reinforcement learning benchmarks with mathematically certified optimal policies, giving researchers a true ground-truth reference for comparing algorithms.
A greybox fuzzing tool uses tool invocation sequences and context bridging to break through LLM agent defenses, finding 33% more injection attacks than black-box baselines.
Genetic programming builds unconventional algebraic multigrid cycles from proven building blocks, outperforming hand tuned solvers by up to 2.1x in hypre benchmarks.
Researchers show that fine-tuning CLIP on unfamiliar domains breaks patch-level alignment far more than image-level alignment, and propose a cycle-consistency fix.
New benchmarks show frontier vision language models confidently confirm subtle false claims buried in long queries, and a DPO recipe cuts hallucinations by up to 24.2%.