DOI first
Every paper on this page has a resolvable DOI. The citation remains valid even if a repository is moved, renamed or archived.
FuryLogic Open Research
FuryLogic Open Research is the publication arm of the company. It holds the papers we have deposited with a DOI, the research questions we are actively working on, and the limits of what we can currently claim.
01 — How this record works
Research software exists to support a claim. We publish the claim, the method and the result as a citable document — and we do not dress a prototype up as a product to make the record look larger.
Every paper on this page has a resolvable DOI. The citation remains valid even if a repository is moved, renamed or archived.
Results state the machine, the model file, the flags and the comparison point. “Faster” is meaningless without the thing it is faster than.
Where a result does not generalise, or a mechanism does not work yet, the paper says so. A gap audit is part of the publication, not an embarrassment.
02 — Publications
Four papers, deposited on Zenodo, maintained by FuryLogic Labs. Each entry links the DOI and, where available, the paper PDF.
A single per-token importance signal, Δ, is extracted from dense hidden-state drift, native SSM selectivity or router-softmax entropy, then used to drive KV cache eviction, sparse attention, head gating and state compression without retraining. Measured at 93.8 % KV cache reduction at 65,536 tokens on one 8 GB GPU across dense, MoE and hybrid model families.
GPU memory is fragmented across cards, and frameworks that spill through the CPU lose a large share of throughput. VUGVA virtualizes multi-GPU VRAM into one pool, transfers with 64-byte DMA descriptors so the CPU never touches payloads, and tiers memory from VRAM to DRAM to SSD with automatic promotion and demotion.
Attention’s scattered KV cache reads carry an 80–84 % bandwidth penalty relative to sequential reads. ASC pairs a predictive attention router with an asynchronous streaming prefetch queue, staging the blocks a kernel will read next into L2 before it asks for them.
A research programme investigating reasoning without gradients, backpropagation, learned embeddings or next-token prediction. Concepts are cavities with mass, displacement and velocity; inference is the propagation of local forces through coupled relations rather than a sampling pass over token probabilities.
Early-stage research programme. Openly documented, including its gaps.
Citation format: Mahir, I. (2026). Title. Zenodo. https://doi.org/10.5281/zenodo.…
03 — Research interests
These are research directions, not product lines. Some have published results; others are open problems where the honest answer is still unknown.
Where time and memory actually go during prefill and decode: batched execution, KV cache residency, prefix reuse, speculative decoding and the scheduling between them.
Dense transformers, mixture-of-experts routing and hybrid state-space attention, studied as families with different compute and memory behaviour rather than one uniform target.
Serving a model across devices that do not share a fast interconnect: memory pooling, expert placement, peer transport and graceful degradation when a node is slow.
Kernel-level work on both sides of the bus: quantized matrix multiplication, DMA descriptors, prefetch scheduling, SIMD, and the cost of moving data rather than computing on it.
A separate research lineage: structural reasoning over a graph-physics substrate, decision readout from settled fields, and systems that defer instead of guessing.
Hybrid lexical and dense retrieval, rank fusion, cross-encoder reranking, and evaluation that can show a retrieval change helping or hurting instead of asserting it.
Databases, kernels, runtimes and protocol surfaces — the layer below the product, where consistency models, memory safety and boot time are the features.
04 — Method
The process is deliberately unglamorous. It exists so a reader can check the work without asking us for permission.
Every claim starts as a number from a named machine and a named model. Where a result does not hold, it is published as a limitation rather than dropped.
A result is only useful if the reason is legible. Papers describe the mechanism precisely enough to be reimplemented or falsified.
Reference implementations accompany the papers so a reader can run the primitive rather than trust the plot.
Preprints are deposited with a DOI and remain citable. Corrections supersede earlier versions instead of quietly replacing them.
On status: Synthetic Intelligence is an early-stage research programme. Its paper is public, its gap audit is public, and it is not offered as a working general-purpose system. We would rather state that plainly than let a reader discover it later.
Engage with the work
We are interested in correspondence that engages with the mechanism: a reproduction that disagrees, a baseline we missed, or a constraint that changes the conclusion.