Cut the cost of agentic LLM memory by deciding what to write before calling an LLM. SAGE is a closed-form novelty gate that routes new facts to ADD, redundant ones to SKIP, and only sends genuinely ambiguous cases to an LLM — 3.4× cheaper, 2.5× faster writes.
A novel teacher‑free distillation method that replaces live teacher inference with compact precomputed random projection teacher fingerprints, enabling storage-efficient, high-performance knowledge transfer and enhanced student training.
A curated research atlas for Efficient ML, AI Infrastructure, and Physical AI
A hands-on lab comparing PTQ INT8, magnitude pruning, and knowledge distillation on small CNNs.
Quantized Defect Correction for low-precision neural operators: precision-sensitive failure diagnosis, selective recovery, and A100 inference evaluation.
Heavy-tail-aware weight-only post-training quantization for vision models, with layer diagnostics, robust quantizers, and reproducible experiments.
Official Repo of OpenArchX Framework.
First 1-bit (BitNet b1.58) recursive reasoner for Sudoku-Extreme - distilled from a 7M-param FP TRM teacher into a 1.4 MB ternary student
Model compression engine built from first principles - magnitude pruning, per-layer sensitivity scanning, and linear quantization (int8/int4/fp8/fp4), benchmarked as a full prune x quantize matrix.
Layer-adaptive quantization of diffusion models using Fisher Information (LAQFI), presented at IEIE 2024.
Paper, results & materials for our NeurIPS 2025 (Workshop on Efficient Reasoning) paper on cost-aware multi-agent orchestration — LoRA-Guided PPO.
Pilot study on post-training quantisation effects for low-resource NMT (Hausa, Swahili, Yoruba) across three model families on consumer GPUs. Prepared for PhD applications 2027.
CPU-first, evidence-first static analysis for suspicious Python source: AST to MalIR to selective micro-model inference.
Kron is a compact English/Russian language model built from Kronecker-product weights. The 2.85M baseline ships as a 3.3 MB int8 artifact; a 10M model on a 2B-token bilingual corpus is in progress. Includes the full research log with negative results and reproducible measurements.
FP8 quantization and token eviction of the KV cache for Llama-3.2-3B (vLLM, kvpress)
Source for my GitHub profile README and its banner graphics: a PhD researcher in Computer Science and Engineering at the University of South Florida working on efficient and generative AI for computer vision and imaging, with links to research such as BAP-MOS, publications, tools and ways to get in touch.
Notes and Labs from MIT 6.5940, (Fall 2023) lecture.
O(N) Linear Complexity Transformer - 125x faster than standard attention using cumulative sum trick. Pure PyTorch implementation.
To associate your repository with the efficient-ml topic, visit your repo's landing page and select "manage topics."