arXiv subjects

Kanav Gupta

Publications and source records attributed to Kanav Gupta.

4 recordsLinked to original sources

arXiv2026

Adaptive Multi-Scale Correlation Meta-Network for Few-Shot Remote Sensing Image Classification

Few-shot learning in remote sensing remains challenging due to three factors: the scarcity of labeled data, substantial domain shifts, and the multi-scale nature of geospatial objects. To address these issues, we introduce Adaptive Multi-Scale Correlation Meta-Network (AMC-MetaNet), a lightweight yet powerful framework with three key innovations: (i) correlation-guided feature pyramids for capturing scale-invariant patterns, (ii) an adaptive channel correlation module (ACCM) for learning dynamic cross-scale relationships, and (iii) correlation-guided meta-learning that leverages correlation patterns instead of conventional prototype averaging. Unlike prior approaches that rely on heavy pre-trained models or transformers, AMC-MetaNet is trained from scratch with only $\sim600K$ parameters, offering $20\times$ fewer parameters than ResNet-18 while maintaining high efficiency ($<50$ms per image inference). AMC-MetaNet achieves up to 86.65\% accuracy in 5-way 5-shot classification on various remote sensing datasets, including EuroSAT, NWPU-RESISC45, UC Merced Land Use, and AID. Our results establish AMC-MetaNet as a computationally efficient, scale-aware framework for real-world few-shot remote sensing.

cs.CV↗

arXiv2025

Dynamic Reasoning Chains through Depth-Specialized Mixture-of-Experts in Transformer Architectures

Contemporary transformer architectures apply identical processing depth to all inputs, creating inefficiencies and limiting reasoning quality. Simple factual queries are subjected to the same multilayered computation as complex logical problems, wasting resources while constraining deep inference. To overcome this, we came up with a concept of Dynamic Reasoning Chains through Depth Specialised Mixture of Experts (DS-MoE), a modular framework that extends the Mixture of Experts paradigm from width-based to depth specialised computation. DS-MoE introduces expert modules optimised for distinct reasoning depths, shallow pattern recognition, compositional reasoning, logical inference, memory integration, and meta-cognitive supervision. A learned routing network dynamically assembles custom reasoning chains, activating only the necessary experts to match input complexity. The dataset on which we trained and evaluated DS-MoE is on The Pile, an 800GB corpus covering diverse domains such as scientific papers, legal texts, programming code, and web content, enabling systematic assessment across reasoning depths. Experimental results demonstrate that DS-MoE achieves up to 16 per cent computational savings and 35 per cent faster inference compared to uniform-depth transformers, while delivering 2.8 per cent higher accuracy on complex multi-step reasoning benchmarks. Furthermore, routing decisions yield interpretable reasoning chains, enhancing transparency and scalability. These findings establish DS-MoE as a significant advancement in adaptive neural architectures, demonstrating that depth-specialised modular processing can simultaneously improve efficiency, reasoning quality, and interpretability in large-scale language models.

cs.CL↗

arXiv2025

Hierarchical Resolution Transformers: A Wavelet-Inspired Architecture for Multi-Scale Language Understanding

Transformer architectures have achieved state-of-the-art performance across natural language tasks, yet they fundamentally misrepresent the hierarchical nature of human language by processing text as flat token sequences. This results in quadratic computational cost, weak computational cost, weak compositional generalization, and inadequate discourse-level modeling. We propose Hierarchical Resolution Transformer (HRT), a novel wavelet-inspired neural architecture that processes language simultaneously across multiple resolutions, from characters to discourse-level units. HRT constructs a multi-resolution attention, enabling bottom-up composition and top-down contextualization. By employing exponential sequence reduction across scales, HRT achieves O(nlogn) complexity, offering significant efficiency improvements over standard transformers. We evaluated HRT on a diverse suite of benchmarks, including GLUE, SuperGLUE, Long Range Arena, and WikiText-103, and results demonstrated that HRT outperforms standard transformer baselines by an average of +3.8% on GLUE, +4.5% on SuperGLUE, and +6.1% on Long Range Arena, while reducing memory usage by 42% and inference latency by 37% compared to BERT and GPT style models of similar parameter count. Ablation studies confirm the effectiveness of cross-resolution attention and scale-specialized modules, showing that each contributes independently to both efficiency and accuracy. Our findings establish HRT as the first architecture to align computational structure with the hierarchical organization of human language, demonstrating that multi-scale, wavelet-inspired processing yields both theoretical efficiency gains and practical improvements in language understanding.

cs.CL↗

arXiv2020

Obtuse Lattice Bases

A lattice reduction is an algorithm that transforms the given basis of the lattice to another lattice basis such that problems like finding a shortest vector and closest vector become easier to solve. We define a class of bases called obtuse bases and show that any lattice basis can be transformed to an obtuse basis. A shortest vector $\mathbf{s}$ can be written as $\mathbf{s}=v_1\mathbf{b}_1+\dots+v_n\mathbf{b}_n$ where $\mathbf{b}_1,\dots,\mathbf{b}_n$ are the input basis vectors and $v_1,\dots,v_n$ are integers. When the input basis is obtuse, all these integers can be chosen to be positive for a shortest vector. This property of obtuse bases makes the lattice enumeration algorithm for finding a shortest vector exponentially faster. We have implemented the algorithm for making bases obtuse, and tested it some small bases.

cs.DS↗