dmitryontech.bsky.social
@dmitryontech.bsky.social
Machine Learning Engineer. I learn by teaching. Opinions are my own.

Building https://bestgpusforai.com
VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval

huggingface.co/papers/2602....
Paper page - VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval
Join the discussion on this paper page
huggingface.co
February 15, 2026 at 11:10 AM
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning

huggingface.co/papers/2602....
Paper page - Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning
Join the discussion on this paper page
huggingface.co
February 13, 2026 at 10:55 AM
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

huggingface.co/papers/2602....
Paper page - Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Join the discussion on this paper page
huggingface.co
February 12, 2026 at 12:29 PM
Code2World: A GUI World Model via Renderable Code Generation

huggingface.co/papers/2602....
Paper page - Code2World: A GUI World Model via Renderable Code Generation
Join the discussion on this paper page
huggingface.co
February 11, 2026 at 11:14 AM
MOVA: Towards Scalable and Synchronized Video-Audio Generation

huggingface.co/papers/2602....
Paper page - MOVA: Towards Scalable and Synchronized Video-Audio Generation
Join the discussion on this paper page
huggingface.co
February 10, 2026 at 10:52 AM
Upgrade Guide: Is the RTX 5080 Worth it for AI Practitioners Still Using the 3080?

open.spotify.com/episode/0vOC...
February 9, 2026 at 4:30 PM
POINTS-GUI-G: GUI-Grounding Journey

huggingface.co/papers/2602....
Paper page - POINTS-GUI-G: GUI-Grounding Journey
Join the discussion on this paper page
huggingface.co
February 9, 2026 at 12:37 PM
The FP4 Advantage: How the RTX 5090 Redefines AI Inference Throughput Over the RTX 4080

open.spotify.com/episode/1mjq...
February 8, 2026 at 6:55 PM
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

huggingface.co/papers/2602....
Paper page - Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Join the discussion on this paper page
huggingface.co
February 8, 2026 at 1:42 PM
Nvidia GPUs with 48 GB Video RAM

medium.com/@javaeeeee/n...
February 8, 2026 at 1:34 PM
Context Forcing: Consistent Autoregressive Video Generation with Long Context

huggingface.co/papers/2602....
Paper page - Context Forcing: Consistent Autoregressive Video Generation with Long Context
Join the discussion on this paper page
huggingface.co
February 6, 2026 at 12:31 PM
RTX 3070 vs. RTX 4060: Raw Power vs. Architectural Efficiency for AI

open.spotify.com/episode/2PMn...
February 5, 2026 at 11:23 PM
Comparing the RTX 4060 Ti and RTX 4070 for AI and Performance

open.spotify.com/episode/2f1e...
February 5, 2026 at 11:16 PM
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

huggingface.co/papers/2602....
Paper page - Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Join the discussion on this paper page
huggingface.co
February 5, 2026 at 12:33 PM
RTX 5070 vs RTX 5080 for AI (TOPS, LLMs, Stable Diffusion) 2026

www.bestgpusforai.com/gpu-comparis...
February 4, 2026 at 10:09 PM
RTX 2080 Super vs 2080 Ti (AI, Deep Learning & CUDA Benchmarks) 2026

www.bestgpusforai.com/gpu-comparis...
February 4, 2026 at 10:08 PM
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding

huggingface.co/papers/2602....
Paper page - CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Join the discussion on this paper page
huggingface.co
February 4, 2026 at 4:19 PM
Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

huggingface.co/papers/2601....
Paper page - Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
Join the discussion on this paper page
huggingface.co
February 3, 2026 at 12:33 PM
PaperBanana: Automating Academic Illustration for AI Scientists

huggingface.co/papers/2601....
Paper page - PaperBanana: Automating Academic Illustration for AI Scientists
Join the discussion on this paper page
huggingface.co
February 2, 2026 at 11:21 AM
The Cache Advantage: How the RTX 4090’s 72MB L2 Cache Redefines AI Efficiency Over the 3090 Ti

open.spotify.com/episode/7nfN...
Spotify – Web Player
open.spotify.com
February 2, 2026 at 11:19 AM
NVIDIA GeForce RTX 3090 Ti vs 4090 for AI (2026): VRAM, Bandwidth, Tensor Cores

www.bestgpusforai.com/gpu-comparis...
February 1, 2026 at 11:06 PM
OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models

huggingface.co/papers/2601....
Paper page - OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models
Join the discussion on this paper page
huggingface.co
February 1, 2026 at 1:24 PM
Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

huggingface.co/papers/2601....
Paper page - Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
Join the discussion on this paper page
huggingface.co
January 30, 2026 at 12:19 PM
DeepSeek-OCR 2: Visual Causal Flow

huggingface.co/papers/2601....
Paper page - DeepSeek-OCR 2: Visual Causal Flow
Join the discussion on this paper page
huggingface.co
January 29, 2026 at 10:45 AM