collaborators

6 papers

cs.CV2026

SE-UNet: Singular Equivariant Imaging for Real-World Constrained Generation

Kanishk Awadhiya

While diffusion models have revolutionized image synthesis, their application to real-world inverse problems is often hampered by the need for massive datasets and the difficulty o…

cs.LG2026

Reasoning as Attractor Dynamics: Latent Memory Retrieval via Gibbs-Weighted Energy Minimization

Kanishk Awadhiya

Large Language Models (LLMs) are traditionally viewed as autoregressive generators. However, from the perspective of collective computation, they function as high-dimensional Dense…

cs.LG2026

Parallel Manifold Steering: Efficient Adaptation of Large Associative Memories via Residual Energy Shaping

Kanishk Awadhiya

Large Transformer models function as Dense Associative Memories (DAMs), retrieving knowledge via high-dimensional attractor dynamics driven by the self-attention mechanism \citep{r…

cs.LG2026

The Fractal Neural Operator: Overcoming Spectral Bias in Chaotic Attractors via Prime-Harmonic Weierstrass Encodings

Kanishk Awadhiya

Deep learning models, particularly Transformers and Neural Operators, exhibit a well-documented "spectral bias," effectively acting as low-pass filters that smooth out high-frequen…

cs.CL2026

Bifocal Attention: Harmonizing Geometric and Spectral Positional Embeddings for Algorithmic Generalization

Kanishk Awadhiya

Rotary Positional Embeddings (RoPE) have become the standard for Large Language Models (LLMs) due to their ability to encode relative positions through geometric rotation. However,…

cs.CV2025

The Inductive Bottleneck: Data-Driven Emergence of Representational Sparsity in Vision Transformers

Kanishk Awadhiya

Vision Transformers (ViTs) lack the hierarchical inductive biases inherent to Convolutional Neural Networks (CNNs), theoretically allowing them to maintain high-dimensional represe…