apple-aiml-research/ml-lensvlm
Official code for LensVLM: Selective Context Expansion for Compressed Visual Representation of Text.
About the project
Official code for LensVLM, a 9B Vision Language Model that scans compressed page images and selectively expands only relevant pages via a read_page tool to answer questions.
Useful for
- Run the bundled HotpotQA demo to inspect the multi-turn page-selection trajectory
- Prepare an eval set from HotpotQA/NQ/Musique with 5x/10x/15x compression and distractors
- Evaluate answer accuracy and page-selection metrics with an LLM judge
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 0 stars so far today, about 4 expected by the end of the day.
- The repository is 4 days old and already has 71 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #188.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 71
- Today
- 0 · ≈ 4 by evening
- Forks
- 5
- Issues and pull requests
- 0
- Watchers
- 0
- Language
- Python
- Created
- September 22, 2026
- Last push
- September 22, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 26, 2026Top new repositories this week: #187
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/apple-aiml-research/ml-lensvlm)More in this category
-
6.9
ollaya-dev/ollaya
A local runtime for decision models: pulls and serves classification and routing models behind a TypeSafe-compatible API. Like Ollama, but for models that return probabilities instead of text.
-
6.4
NVIDIA/Model-Optimizer
NVIDIA library for compressing and accelerating models: quantization, pruning, distillation, NAS and speculative decoding with export to TensorRT-LLM, vLLM, SGLang. For ML engineers preparing models for deployment.
-
5.4
nokia-applied-research/AnyJev
Turns any LLM into a decision model with typed questions (choice, yes/no, score) that return real probabilities read from the next-token distribution, without training. L0 removes position and label-prior bias; L1 adds…
-
4.7
Badtheorylabs/interference-search
A search method that reasons over explicit states instead of a language model's linear transcript: many branches expand at once, duplicates merge, dead ends are dropped by a trained judge, and survivors advance…
-
4.4
Liuziyu77/Valen
A multimodal decision model built on a Qwen3.5-0.8B/2B backbone: it takes text, images and video with an instruction and returns probabilities over supplied candidates without generating answer tokens. The repo…
-
4.3
mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.