Search: github.com/vlm | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Replace OCR with Vision Language Models (github.com/vlm-run)

292 points

a year ago

2.

Run structured extraction on documents/images locally with Ollama and Pydantic (github.com/vlm-run)

170 points

a year ago

3.

A Node.js SDK for calling Vision Language Models (github.com/vlm-run)

6 points

a year ago

4.

Unified Vision-Language Agents – Detect, Segment, OCR, Generate and More (github.com/vlm-run)

5 points

6 months ago

5.

Show HN: Visually parse an entire YouTube video frame by frame (github.com/vlm-run)

5 points

a year ago

6.

Vlms-zero-to-hero: readings from the fundamentals to the cutting edge of VLMS (github.com/SkalskiP)

2 points

a year ago

7.

Experimental Optical Encoder for Qwen3-VLM-2B-Instruct (github.com/Volkopat)

1 point

7 months ago

8.

Asn1c: The Lionet ASN.1 Compiler (github.com/vlm)

1 point

7 months ago

9.

Show HN: r1_vlm – Open-Source Framework for Visual Reasoning with GRPO (github.com/groundlight)

5 points

a year ago

10.

Mlx-VLM: Fast Local VLMs and Omni Models on Apple Silicon with MLX (github.com/Blaizzy)

2 points

2 months ago

11.

Show HN: I achieved over 10% improvement on 3D vision PointCLIP (github.com/genji970)

2 points

a year ago

12.

Show HN: 2500 vision benchmarks / evals for Vision Language Models (github.com/Overshoot-ai)

1 point

zakariaelhjouji

2 months ago

13.

Show HN: Vlm in 3D PC, 16 shot scanobjectnn top1 acc: 99.91 (github.com/genji970)

1 point

a year ago

14.

Super fast and accurate image classification on edge devices (github.com/Paulescu)

1 point

8 months ago

15.

Show HN: Benchmarking VLMs vs. Traditional OCR (getomni.ai)

146 points

a year ago

16.

Show HN: LoongForge-A high-performance training framework for LLM, VLM, VLA, Wan (github.com/baidu-baige)

10 points

14 days ago

17.

Show HN: Cursed Browser – a VLM reads the HTML and hallucinates the page (github.com/scosman)

7 points

10 days ago

18.

Cursed_browser: Web browser with a VLM as rendering engine (github.com/scosman)

4 points

a month ago

19.

SketchVLM: Letting VLMs draw on images while explaining their reasoning (github.com/Brandon-Collins7)

3 points

a month ago

20.

Show HN: Unsiloed Chunker – VLM powered semantic chunking for RAG (github.com/Unsiloed-AI)

3 points

a year ago

21.

Show HN: Vision AI Checkup, an Optometrist for VLMs (visioncheckup.com)

2 points

a year ago

22.

The simplest, fastest repository for training/finetuning small-sized VLMs (github.com/huggingface)

2 points

a year ago

23.

Advanced Quantization Algorithm for LLMs/VLMs (github.com/intel)

2 points

a year ago

24.

Show HN: LLM / VLM language agent implementations (github.com/arthurcolle)

2 points

a year ago

25.

Show HN: A VLM-powered image search engine built with Ruby on Rails (github.com/neonwatty)

2 points

a year ago

26.

Show HN: A/B test your own VLMs for document parsing (Self-hosted Arena) (github.com/Bae-ChangHyun)

1 point

4 months ago

27.

Show HN: Offline AI Photo Search (local VLM and semantic search) (github.com/Pankaj4152)

1 point

6 months ago

28.

"Captions With Attitude" in the browser from local VLM using llama.cpp in Go (github.com/hybridgroup)

1 point

7 months ago

29.

Pure Go hardware accelerated local inference on VLMs using llama.cpp (github.com/hybridgroup)

1 point

7 months ago

30.

Yzma = embedding+inference on VLM/LLM/SLM/TLM in pure Go using llama.cpp (github.com/hybridgroup)

1 point

8 months ago