← Search

Karan Dalal

2 accepted papers

2025

Learning to (Learn at Test Time): RNNs with Expressive Hidden States

ICML 2025spotlight

Self-attention performs well in long context but has quadratic complexity. Existing RNN layers have linear complexity, but their performance in long context is limited by the expressive power of their hidden states. We present a practical framework for instantiating sequence modeling layers with lin…

2025

One-Minute Video Generation with Test-Time Training

CVPR 2025poster

Transformers today still struggle to generate one-minute videos because self-attention layers are inefficient for long context. Alternatives such as Mamba layers struggle to produce coherent scenes because their hidden states are small and less expressive. We experiment with Test-Time Training (TTT)…