3 papers
cs.LG2025
Do traveling waves make good positional encodings?
Chase van de Geijn, Ayush Paliwal, Timo Lüddecke +1
Transformers rely on positional encoding to compensate for the inherent permutation invariance of self-attention. Traditional approaches use absolute sinusoidal embeddings or learn…
cs.LG2025
Clifford Algebraic Rotor Embeddings : Maybe embeddings should start to CARE
Sameeksha Sriram, Ayush Paliwal, Alexander S. Ecker +1
Rotary Positional Embeddings (RoPE) have demonstrated exceptional performance as a positional encoding method, consistently outperforming their baselines. While recent work has sou…
cs.CV2025
FLASHμ: Fast Localizing And Sizing of Holographic Microparticles
Ayush Paliwal, Oliver Schlenczek, Birte Thiede +5
Reconstructing the 3D location and size of microparticles from diffraction images - holograms - is a computationally expensive inverse problem that has traditionally been solved us…