MarkTechPost
MarkTechPost publishes articles covering AI, developer, guide, tutorial. A trusted source for AI and technology insights.
Profile generated by AI for Anything
Datalab’s Marker 2 vs MinerU, Docling and LiteParse: 76.0 on olmOCR-bench at 5× MinerU’s Throughput
10m
Building an OCR Pipeline with Baidu's Unlimited-OCR: Overview of Gundam and Base Inference Modes
21h
Claude API may silently route requests to different model weights than requested
1d
The original title is: "Best Open Speech Recognition (ASR) Models in 2026: WER, Languages, Latency, and License Compared"
1d
The original title is "EdgeBench: A Practical Benchmark for Evaluating AI Agents"
2d
Google Releases Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber: A Cheaper, More Token-Efficient Flash Tier Built for Agentic Workloads
3d
Validating Distributed LLM Serving Benchmarks with NVIDIA srt-slurm, SLURM Recipes, Parameter Sweeps, and Pareto Analysis
3d
Community dev fine-tunes MiniCPM5-1B on Claude Fable 5 traces for 657MB local reasoning model
5d
Alibaba Previews Qwen3.8-Max, a 2.4 Trillion-Parameter Multimodal Model, Days After Moonshot’s Kimi K3 Open-Weight Launch
5d
Perplexity AI Releases WANDR: An Open Benchmark Evaluating Research Agents That Must Search Wide And Deep
5d
Fine-Tuning Qwen3 with LoRA Using NVIDIA NeMo AutoModel: A Complete Single-GPU Google Colab Workflow Tutorial
6d
Google Cloud Releases Always-On Memory Agent Reference Implementation on Gemini 3.1 Flash-Lite
6d
Sakana AI’s Error Diffusion Trains Dale-Compliant Dual-Stream Networks, Reaching 96.7% MNIST and 61.7% CIFAR-10 Without Backpropagation
6d
Build an Agentic Event Venue Operator with MongoDB Atlas, Voyage, and LangGraph
7d
The original title is a tutorial headline about building an AI agent for event venue operations using specific technologies.
7d
OpenAI Details GPT-Red: An Internal Automated Red-Teaming Model That Beat Human Red-Teamers 84% To 13% On Prompt Injection
8d
Patter SDK Guide to Building a Restaurant Booking Phone Agent with Dynamic Variables, Guardrails, Latency Dashboards, and Eval Checks
8d
Building a Gin Config Controlled PyTorch Pipeline with Configurable MLP Variants, Cosine Scheduling, and Runtime Parameter Overrides
9d
Mistral AI Releases Robostral Navigate: An 8B Model Enabling Robots to Navigate Complex Environments Using a Single RGB Camera
10d
Building a VideoAgent-Style Multi-Agent System: Intent Parsing, Graph Planning, and Tool Routing for Video Editing Tasks
11d
Stanford Researchers Introduce TRACE: A Capability-Targeted Agentic Training System That Turns Recurrent Agent Failures Into Synthetic RL Environment
11d
Mira Murati’s Thinking Machines Lab Makes The Technical Case For Human-Centered AI Built On Customizable Model Weights
13d
The original title is: "A Coding Guide to NVIDIA's Tile-Based GPU Programming: From cuTile and Triton Kernels to Flash Attention"
13d
Ant Group’s Robbyant Unveils LingBot-VA 2.0: A Causal Video-Action Model Built Natively for Physical AI
13d