2 papers
cs.CL2026
Reinforced Fast Weights with Next-Sequence Prediction
Hee Seung Hwang, Xindi Wu, Sanghyuk Chun +1
Fast weight architectures offer a promising alternative to attention-based transformers for long-context modeling by maintaining constant memory overhead regardless of context leng…
cs.CV2025
Visual Compositional Tuning
Xindi Wu, Hee Seung Hwang, Polina Kirichenko +2
Visual instruction tuning (VIT) datasets have grown rapidly in scale, yet the informativeness of individual training samples has largely been overlooked. Recent dataset selection m…