Exploiting Biases in Attention for Transformers
cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/EIDOSLAB/AttentionWithBias
Terminology
Sources
- Rethinking Attention with Performers
- Deep Residual Learning for Image Recognition
- Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
- Training data-efficient image transformers & distillation through attention
- Attention Is All You Need
- SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
- Deformable DETR: Deformable Transformers for End-to-End Object Detection
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis