LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems

The field of artificial intelligence has undergone a revolution from foundational Transformer architectures to reasoning-capable systems approaching human-level performance. We present LLMOrbit, a comprehensive circular taxonomy navigating the landscape of large language models spanning 2019-2025. This survey examines over 50 models across 15 organizations through eight interconnected orbital dimensions, documenting architectural innovations, training methodologies, and efficiency patterns defining modern LLMs, generative AI, and agentic systems. We identify three critical crises: (1) data scarcity (9-27T tokens depleted by 2026-2028), (2) exponential cost growth ($3M to $300M+ in 5 years), and (3) unsustainable energy consumption (22x increase), establishing the scaling wall limiting brute-force approaches. Our analysis reveals six paradigms breaking this wall: (1) test-time compute (o1, DeepSeek-R1 achieve GPT-4 performance with 10x inference compute), (2) quantization (4-8x compression), (3) distributed edge computing (10x cost reduction), (4) model merging, (5) efficient training (ORPO reduces memory 50%), and (6) small specialized models (Phi-4 14B matches larger models). Three paradigm shifts emerge: (1) post-training gains (RLHF, GRPO, pure RL contribute substantially, DeepSeek-R1 achieving 79.8% MATH), (2) efficiency revolution (MoE routing 18x efficiency, Multi-head Latent Attention 8x KV cache compression enables GPT-4-level performance at <$0.30/M tokens), and (3) democratization (open-source Llama 3 88.6% MMLU surpasses GPT-4 86.4%). We provide insights into techniques (RLHF, PPO, DPO, GRPO, ORPO), trace evolution from passive generation to tool-using agents (ReAct, RAG, multi-agent systems), and analyze post-training innovations.

Spectral Convolutional Transformer: Harmonizing Real vs. Complex Multi-View Spectral Operators for Vision Transformer

Transformers used in vision have been investigated through diverse architectures - ViT, PVT, and Swin. These have worked to improve the attention mechanism and make it more efficient. Differently, the need for including local information was felt, leading to incorporating convolutions in transformers such as CPVT and CvT. Global information is captured using a complex Fourier basis to achieve global token mixing through various methods, such as AFNO, GFNet, and Spectformer. We advocate combining three diverse views of data - local, global, and long-range dependence. We also investigate the simplest global representation using only the real domain spectral representation - obtained through the Hartley transform. We use a convolutional operator in the initial layers to capture local information. Through these two contributions, we are able to optimize and obtain a spectral convolution transformer (SCT) that provides improved performance over the state-of-the-art methods while reducing the number of parameters. Through extensive experiments, we show that SCT-C-small gives state-of-the-art performance on the ImageNet dataset and reaches 84.5\% top-1 accuracy, while SCT-C-Large reaches 85.9\% and SCT-C-Huge reaches 86.4\%. We evaluate SCT on transfer learning on datasets such as CIFAR-10, CIFAR-100, Oxford Flower, and Stanford Car. We also evaluate SCT on downstream tasks i.e. instance segmentation on the MSCOCO dataset. The project page is available on this webpage.\url{https://github.com/badripatro/sct}

SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series

Transformers have widely adopted attention networks for sequence mixing and MLPs for channel mixing, playing a pivotal role in achieving breakthroughs across domains. However, recent literature highlights issues with attention networks, including low inductive bias and quadratic complexity concerning input sequence length. State Space Models (SSMs) like S4 and others (Hippo, Global Convolutions, liquid S4, LRU, Mega, and Mamba), have emerged to address the above issues to help handle longer sequence lengths. Mamba, while being the state-of-the-art SSM, has a stability issue when scaled to large networks for computer vision datasets. We propose SiMBA, a new architecture that introduces Einstein FFT (EinFFT) for channel modeling by specific eigenvalue computations and uses the Mamba block for sequence modeling. Extensive performance studies across image and time-series benchmarks demonstrate that SiMBA outperforms existing SSMs, bridging the performance gap with state-of-the-art transformers. Notably, SiMBA establishes itself as the new state-of-the-art SSM on ImageNet and transfer learning benchmarks such as Stanford Car and Flower as well as task learning benchmarks as well as seven time series benchmark datasets. The project page is available on this website ~\url{https://github.com/badripatro/Simba}.