Similar Items: Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime
- Trust, but Verify: Peeling Low-Bit Transformer Networks for Training Monitoring
- Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime
- Spiking Sequence Machines and Transformers
- Fast Byte Latent Transformer
- Transformers with Selective Access to Early Representations
- Taming Outlier Tokens in Diffusion Transformers