🔄 In a Training Loop

Nikita Davidchuk

Ar4ikov

·

https://github.com/Ar4ikov

Ar4ikov

AI & ML interests

nlp, web, opensource, transformers, asr, ser, tts, cv

Recent Activity

liked a Space about 6 hours ago

FineEnvs/multi-harness-rl

liked a Space 4 days ago

24yearsold/see-through-demo

liked a model 5 days ago

XingChen-AGI/TeleOCR

View all activity

Organizations

upvoted a collection 15 days ago

V100-Validated Quantizations

Models built for and runtime-validated on NVIDIA Tesla V100/SM70, with frozen recipes, checksums, benchmarks, and explicit quality limits. • 8 items • Updated 26 days ago • 4

upvoted a paper 20 days ago

How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus

Paper • 2609.15504 • Published 22 days ago • 37

upvoted an article 28 days ago

Article

TurboQuant Quantization Explained

lucifertrj

•

29 days ago

• 6

upvoted a collection 2 months ago

Audio Models Quantized

INT8, FP8 and INT4 builds of the Aniemore speech-emotion models. Load one with from_pretrained(repo, subfolder="int4"). • 9 items • Updated Aug 1 • 1

upvoted 2 collections 7 months ago

T-One Finetuned

T-One fine-tuned models on corporative internal expert-labeled data • 5 items • Updated Feb 26 • 1

Whisper Finetuned

OpenAI's Whisper models fine-tuned on corporative internal expert-labeled data • 3 items • Updated Feb 26 • 1

upvoted a paper 8 months ago

VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection

Paper • 2512.07533 • Published Dec 8, 2025 • 4

upvoted an article 8 months ago

Article

Transformers v5: Simple model definitions powering the AI ecosystem

+2

lysandre, ArthurZ, cyrilvallez, reach-vb

•

Dec 1, 2025

• 315

upvoted a paper 9 months ago

WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference

Paper • 2512.22737 • Published Dec 28, 2025 • 2

upvoted a paper 11 months ago

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published Nov 19, 2025 • 236

upvoted a paper 12 months ago

Qwen2.5-Omni Technical Report

Paper • 2503.20215 • Published Mar 26, 2025 • 174

upvoted an article 12 months ago

Article

How Financial News Can Be Used to Train Good Financial Models

SelmaNajih001

•

Oct 8, 2025

• 10

upvoted 2 articles about 1 year ago

Article

SOTA OCR with Core ML and dots.ocr

FL33TW00D-HF, pcuenq

•

Oct 2, 2025

• 65

Article

Introducing RTEB: A New Standard for Retrieval Evaluation

+4

fzliu, KennethEnevoldsen, Samoed, isaacchung, tomaarsen, fzoll

•

Oct 1, 2025

• 149

upvoted 3 papers about 1 year ago

Learning the CSI Recovery in FDD Systems

Paper • 2104.01322 • Published Apr 3, 2021 • 1

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25, 2025 • 222

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Paper • 2508.05004 • Published Aug 7, 2025 • 135

upvoted an article about 1 year ago

Article

Introducing ColQwen-Omni: Retrieve in every modality

manu

•

Jul 17, 2025

• 78

upvoted a collection over 1 year ago

Cosmos-Preidct1

⚠️ This collection is archived. 👉 https://huggingface.co/collections/nvidia/cosmos3 • 14 items • Updated Aug 11 • 302

upvoted a collection almost 2 years ago

Spaces for Audio / Voices

539 items • Updated 25 days ago • 32