arXiv subjects

Aryan Karmore

Publications and source records attributed to Aryan Karmore.

3 recordsLinked to original sources

arXiv2026

ButterflyViT: 354$\times$ Expert Compression for Edge Vision Transformers

Deploying sparse Mixture of Experts(MoE) Vision Transformers remains a challenge due to linear expert memory scaling. Linear memory scaling stores $N$ independent expert weight matrices requiring $\mathcal{O}(N_E \cdot d^2)$ memory, which exceeds edge devices memory budget. Current compression methods like quantization, pruning and low-rank factorization reduce constant factors but leave the scaling bottleneck unresolved. We introduce ButterflyViT, a method that treats experts not as independent weight matrices but as geometric reorientations of a unified shared quantized substrate. Diversity among experts arises from viewing different angles of shared capacity, not from redundant storage. By applying learned rotations to a shared ternary prototype, each expert yields $\mathcal{O}(d_{\text{model}} \cdot d_{\text{ff}} + N_E \cdot n_\ell \cdot d)$ memory which is sub-linear in the number of experts. To address the unique challenges of vision, a spatial smoothness regulariser is introduced that penalises routing irregularities between adjacent patch tokens, turning patch correlation into a training signal. Across image classification tasks on CIFAR-100, ButterflyViT achieves 354$\times$ memory reduction at 64 experts with negligible accuracy loss. ButterflyViT allows multiple experts to fit on edge-constrained devices showing that geometric parameterization breaks linear scaling.

cs.CV↗

arXiv2026

ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits

In current Mixture of Experts (MoE) architectures, linear memory scaling is present, the memory grows as the number of experts increases. $N$ independent expert weight matrices require $\mathcal{O}(N \cdot d^2)$ memory which exceeds the memory budget of edge devices. Current compression methods like quantization, pruning, and low-rank factorization reduce constant factors, but the scaling bottleneck is still unresolved. We introduce ButterflyMoE, a method which treats experts not as independent matrices but as geometric reorientations of a shared quantized substrate. Diversity amongst the experts arises from viewing different angles of the shared capacity and not from redundant storage. Learned rotations are applied to a shared ternary prototype. With this, each expert yields $\mathcal{O}(d^2 + N \cdot d \log d)$ memory-reducing per-expert cost from $\mathcal{O}(d^2)$ to $\mathcal{O}(d \log d)$. The key insight is that training these rotations with quantization reduces activation outliers and stabilizes extreme low-bit training where other static methods collapse. Across language modeling benchmarks, ButterflyMoE achieves 80$\times$ memory reduction at 8 experts with a highly favorable memory-accuracy tradeoff.At this 80x compression ButterflyMoE outperforms an equal memory dense baseline, showing that orbital parameterization extracts fundamentally more utility per byte. When scaled up to 256 experts, ButterflyMoE asymptotically compresses the memory by 150 $\times$. ButterflyMoE reduces the constant factor of linear scaling with compression ratio growing with the expert count.

cs.LG↗

arXiv2026

LOOKAT: Lookup-Optimized Key-Attention for Memory-Efficient Transformers

Compressing the KV cache is a required step to deploy large language models on edge devices. Current quantization methods compress storage but fail to reduce bandwidth as attention calculation requires dequantizing keys from INT4/INT8 to FP16 before use. We observe that attention scoring is mathematically equivalent to the inner product similarity search and we can apply some compression techniques from vector databases to compress KV-cache better. We propose LOOKAT, which applies product quantization and asymmetric distance computation, to transformer architecture by decomposing key vectors into subspaces, learning codebooks and computing attention tables via lookup tables. This transforms attention from memory-bound to compute-bound. LOOKAT achieves 64 $\times$ compression at 95.7\% output fidelity and 32 $\times$ compression at 95.0\% fidelity when tested on GPT-2. LOOKAT requires no architecture changes or training while maintaining rank correlation $\rho > 0.95$. Theoretical analysis confirms that rank correlation degrades as $O(d_k/mK)$, with guarantees validated across sequence lengths up to 1024 tokens.

cs.LG↗