- Yapay Zeka · arxiv/cs.LG · 4 dk
Selective-Update RNNs Match Transformers While Using Less Memory
A new RNN architecture learns when to update internal state, preserving memory across long sequences and reducing computational waste on redundant input.
3 Mayıs 2026 Oku → → - Yapay Zeka · arxiv/cs.AI · 4 dk
Transformer agents embed four systematic biases into recommendations
Attention mechanisms in AI recommenders amplify recency, popularity, and synthetic data effects, creating reliability risks invisible to standard metrics.
1 Mayıs 2026 Oku → → - Yapay Zeka · arxiv/cs.LG · 8 dk
Model Architecture Controls Whether Errors Stay Hidden
Transformer design determines if internal decision signals remain observable after training, independent of output confidence metrics.
29 Nisan 2026 Oku → → - Yapay Zeka · arxiv/cs.AI · 5 dk
Transformers learn graph connectivity selectively, not universally
New research shows transformers can infer transitive relations on grid-structured graphs but fail on fragmented ones, with scaling helping only certain architectures.
23 Nisan 2026 Oku → → - Mühendislik · arxiv/cs.AI · 4 dk
Dual Transformers Improve Bug Assignment Accuracy by 10%+
TriagerX uses two transformer models and developer interaction history to recommend the right engineer for bug fixes, outperforming single-model approaches.
20 Nisan 2026 Oku → → - Yapay Zeka · arxiv/cs.LG · 8 dk
Distilling Transformers into Mamba via Linearized Attention
A two-stage knowledge transfer method preserves Transformer performance in State Space Models by routing through linearized attention as an intermediate step.
17 Nisan 2026 Oku → → - Yapay Zeka · arxiv/cs.LG · 8 dk
Three-Phase Transformer: Structural Prior for Decoder Efficiency
A residual-stream architecture using cyclic channel partitioning and phase-aligned rotations achieves 7% perplexity gains with minimal parameter overhead.
17 Nisan 2026 Oku → → - Yapay Zeka · arxiv/cs.LG · 3 dk
Transformer models outperform CNNs in prostate MRI segmentation
SwinUNETR achieves 5-point Dice improvement over standard UNet when trained on mixed-reader datasets, suggesting transformer attention handles annotation variability better.
17 Nisan 2026 Oku → →