8 papers
Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention
Julien Siems, Riccardo Grazzi, Korbinian Pöppel +8
Linear RNNs based on the delta-rule enable efficient sequence modeling, but their linear updates with a low-rank correction constrain their expressivity. Prior work has shown that…
Selective Rotary Position Embedding
Sajad Movahedi, Timur Carstensen, Arshia Afzal +3
Position information is essential for language modeling. In softmax transformers, Rotary Position Embeddings (\textit{RoPE}) encode positions through \textit{fixed-angle} rotations…
TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting
Vladyslav Moroshan, Julien Siems, Arber Zela +2
Foundation models for zero-shot time series forecasting face challenges in efficient long-horizon prediction and reproducibility, with existing synthetic-only approaches underperfo…
Where to Begin: Efficient Pretraining via Subnetwork Selection and Distillation
Arjun Krishnakumar, Rhea Sanjay Sukthanker, Hannan Javed Mahadik +5
Small Language models (SLMs) offer an efficient and accessible alternative to Large Language Models (LLMs), delivering strong performance while using far fewer resources. We introd…
Open-sci-ref-0.02: open reference baselines for reproducible language model and dataset comparison
Marianna Nezhurina, Harsh Raj, Jörg Franke +7
Reliable progress in language modeling depends on knowing whether a new dataset, architecture, or training recipe is genuinely better than existing alternatives. To foster reproduc…
Quickly Tuning Foundation Models for Image Segmentation
Breenda Das, Lennart Purucker, Timur Carstensen +1
Foundation models like SAM (Segment Anything Model) exhibit strong zero-shot image segmentation performance, but often fall short on domain-specific tasks. Fine-tuning these models…
Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization
Timur Carstensen, Neeratyoy Mallik, Frank Hutter +1
As model sizes grow, finding efficient and cost-effective hyperparameter optimization (HPO) methods becomes increasingly crucial for deep learning pipelines. While multi-fidelity H…
DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
Julien Siems, Timur Carstensen, Arber Zela +3
Linear Recurrent Neural Networks (linear RNNs) have emerged as competitive alternatives to Transformers for sequence modeling, offering efficient training and linear-time inference…