ZK
Editor-in-Chief · CPO of AlpinaGPT

Zhemal Khamidun

Head of AI at Alpina Digital, CPO of AlpinaGPT (~30-person engineering & AI team). Founder of Vibe Academy & Hamidun Consulting, author of the AI channel «Готовим ИИшницу» (@jemal_hamidun).

10,639Published articles
50+Verified primary sources
6Language editions (RU/EN/ES/PT/FR/AR)
SWIM saves compute: audio-video generation gains up to 30.7% over Best-of-N
Research·arXiv cs.CV

SWIM saves compute: audio-video generation gains up to 30.7% over Best-of-N

Oct 12, 2026·2 min
SAM 2.1 fine-tuned on facades and interiors: mIoU rises from 49.9% to 69.6%
LLM

SAM 2.1 fine-tuned on facades and interiors: mIoU rises from 49.9% to 69.6%

Oct 12, 2026·2 min
SAIL Keeps Its Target in Frame Using Audio and Text, and Beats Rivals on Two Benchmarks
Research

SAIL Keeps Its Target in Frame Using Audio and Text, and Beats Rivals on Two Benchmarks

Oct 12, 2026·2 min
Wearable Stereo Camera Estimates Food Volume With 9.1% Error, No Reference Object Needed
Hardware

Wearable Stereo Camera Estimates Food Volume With 9.1% Error, No Reference Object Needed

Oct 12, 2026·2 min
Researchers Compare CNN, ViT and Mamba Attention Against Human Gaze
Research·arXiv cs.CV

Researchers Compare CNN, ViT and Mamba Attention Against Human Gaze

Three architectures, three domains, three metrics: eye tracking shows CNNs look broadly, ViTs lock onto micro-features, and Mamba is strong in medicine but diverges…

Oct 12, 2026·3 min
Stroop Test Shows VLMs Read the Text in an Image Before They See the Color
Research·arXiv cs.CV

Stroop Test Shows VLMs Read the Text in an Image Before They See the Color

Researchers ran contrastive and generative VLMs through the classic Stroop test. When text and color conflict, the models more often answer with the written word.

Oct 12, 2026·2 min
ForcingBooster Halves Denoising Steps in Autoregressive Video Generation
Research·arXiv cs.CV

ForcingBooster Halves Denoising Steps in Autoregressive Video Generation

ForcingBooster assigns denoising steps per patch, so simple regions stop early. The result: roughly 50% fewer steps at quality comparable to a four-step baseline.

Oct 12, 2026·2 min
MemReg Outperforms Pairwise Methods and SLAM in LiDAR Point Cloud Registration
Robotics·arXiv cs.CV

MemReg Outperforms Pairwise Methods and SLAM in LiDAR Point Cloud Registration

The new MemReg network registers LiDAR scans as a stream, not in pairs. Two memory buffers deliver the best results on KITTI, nuScenes and Apollo-Southbay. The code…

Oct 12, 2026·2 min
Top themes
01Video-Language Models Confuse Car Maneuvers: LoRA and Probes Fix the ErrorOct 12, 2026·2 min02MIRAGE anchors video-based 3D reconstruction to LiDAR and beats COLMAP on three datasetsOct 12, 2026·2 min03OMNI: One Compact Encoder Absorbs the Knowledge of 10 Models for PathologyOct 12, 2026·2 min04TerraAgent checks whether the AI actually looks at the image: hallucinations drop from 17.1% to 9.8%Oct 12, 2026·2 min05AVA improves multimodal ICL accuracy by 1.7 points without any trainingOct 12, 2026·2 min
Coral-KV Compresses Video Model KV-Cache by 37–48% and Lifts PSNR by Up to 4.95 dB
Research·arXiv cs.CV

Coral-KV Compresses Video Model KV-Cache by 37–48% and Lifts PSNR by Up to 4.95 dB

Oct 12, 2026·2 min
Black Lake: Chinese Factories Skip Digitization and Go Straight to AI Agents
Business·SCMP Tech

Black Lake: Chinese Factories Skip Digitization and Go Straight to AI Agents

Oct 12, 2026·2 min
T. Rowe Price: 55% of Hong Kong Residents Expect AI to Hit Their Retirement, but Only One in Five Feels Ready
Business·SCMP Tech

T. Rowe Price: 55% of Hong Kong Residents Expect AI to Hit Their Retirement, but Only One in Five Feels Ready

Oct 12, 2026·2 min
Genetic Optimizer Cuts Aerosol Sensor Placement Time in the UK by 60%
Research·arXiv cs.LG

Genetic Optimizer Cuts Aerosol Sensor Placement Time in the UK by 60%

Oct 12, 2026·2 min
Kronecker Product Attention Compresses the KV-Cache Up to 10x and Matches MLA on Quality
Research·arXiv cs.LG

Kronecker Product Attention Compresses the KV-Cache Up to 10x and Matches MLA on Quality

An arXiv preprint proposes KPA, which stores keys and values as sums of Kronecker products. It claims up to 10x KV-cache compression with quality on par with MHA…

Oct 12, 2026·2 min
TimesFM 3.0 Cuts University Building Energy Forecast Error by 43%
Research·arXiv cs.LG

TimesFM 3.0 Cuts University Building Energy Forecast Error by 43%

Pretrained TimesFM 3.0, with no local fine-tuning, cut day-ahead MAE for a university building by 43% versus a naive baseline. XGBoost stays close behind.

Oct 12, 2026·2 min
Wasserstein BaryBooster Turns Diffusion Realism into Event Forecast Accuracy
Research·arXiv cs.LG

Wasserstein BaryBooster Turns Diffusion Realism into Event Forecast Accuracy

The authors recast event-sequence forecasting as conditional generation and show that no method wins on both accuracy and realism. BaryBooster offers a way out.

Oct 12, 2026·2 min
DiffusionART speeds up RL fine-tuning of video models 12x, with no EMA tuning
LLM·arXiv cs.LG

DiffusionART speeds up RL fine-tuning of video models 12x, with no EMA tuning

Oct 12, 2026·2 min
A Physical Transformer Built Entirely From Transistors Learns In-Context Learning in Simulation
Research·arXiv cs.LG

A Physical Transformer Built Entirely From Transistors Learns In-Context Learning in Simulation

Oct 12, 2026·2 min
Theory Shows Masked Diffusion on Transformers Learns from Õ(LK/ε) Samples
Research·arXiv cs.LG

Theory Shows Masked Diffusion on Transformers Learns from Õ(LK/ε) Samples

Oct 12, 2026·2 min
SAZO speeds up LLM fine-tuning without backprop: up to 6× fewer queries to reach the same loss
Research·arXiv cs.LG

SAZO speeds up LLM fine-tuning without backprop: up to 6× fewer queries to reach the same loss

Oct 12, 2026·2 min
Holomorphic Neural Networks With Singular Functions Beat All Methods on Laplace Benchmarks
Research·arXiv cs.LG

Holomorphic Neural Networks With Singular Functions Beat All Methods on Laplace Benchmarks

Oct 12, 2026·2 min
Cox Regression Learns From Truncated Data Orders of Magnitude Faster Than EM
Research

Cox Regression Learns From Truncated Data Orders of Magnitude Faster Than EM

Oct 12, 2026·2 min
CacheScope speeds up diffusion models by up to 3.57x and cuts LPIPS by 70%
Research

CacheScope speeds up diffusion models by up to 3.57x and cuts LPIPS by 70%

Oct 12, 2026·2 min
AI Error in Estimating Hidden Solar Generation Rises from 0.104 to 0.185 kW
Research

AI Error in Estimating Hidden Solar Generation Rises from 0.104 to 0.185 kW

Oct 12, 2026·2 min
CircuitTree assembles 39 HuBERT phoneme circuits into a syllable transcriber with 64.8% accuracy
Research·arXiv cs.LG

CircuitTree assembles 39 HuBERT phoneme circuits into a syllable transcriber with 64.8% accuracy

A new algorithm merges small HuBERT subnetworks into a single model. It recognizes open syllables with 64.8% accuracy, and 99.5% of the circuit components are…

Oct 12, 2026·2 min
ResonatorLM Taught to Read Memory by Token: Perplexity at 1024 Drops from 12.81 to 3.76
Research·arXiv cs.LG

ResonatorLM Taught to Read Memory by Token: Perplexity at 1024 Drops from 12.81 to 3.76

ResonatorLM's read phase now depends on the current token, at a cost of 0.2% more parameters. Trained on 256 tokens and tested on 1024, perplexity fell from 12.81…

Oct 12, 2026·2 min