collaborators

5 papers

cs.AI2026

Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement

Alec Helbling, Andrey Bryutkin, Mauro Martino +2

Discrete flow models have recently shown promising performance on few-step text generation; however, when naively applied to structured reasoning tasks such as Sudoku and Zebra puz…

cs.CV2026

Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers

Kabir Swain, Sijie Han, Daniel Karl I. Weidele +2

Transformers process images and videos by flattening space and time into long token sequences. While attention and KV caching preserve past features, their memory grows with sequen…

cs.LG2026

Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression

Kabir Swain, Sijie Han, Daniel Karl I. Weidele +3

We propose \textbf{Hurwitz Quaternion Multiplicative Quantization (HQMQ)}, a \textbf{calibration-free} method for KV cache compression of large language models. HQMQ treats each 4-…

cs.LG2026

Tensor Cache: Eviction-conditioned Associative Memory for Transformers

Kabir Swain, Sijie Han, Daniel Karl I. Weidele +2

Autoregressive Transformer KV caches grow linearly with context length; sliding-window caching bounds memory but discards evicted tokens entirely, so relevant evidence outside the…

cs.LG2026

Small Models, Smarter Learning: The Power of Joint Task Training

Csaba Both, Benjamin Hoover, Hendrik Strobelt +4

Multi-task learning improves generalization, but when does it reduce the model capacity required to learn? We provide a systematic study of how joint training affects the learning…