Open-Weight Models

Model

vision-language-pretraining-baseline

Heitor L. Santos

A structured set of research notes on Vision Language Pretraining, with concrete evaluation references and open questions. Plans and hypotheses are kept separate from completed results. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with review.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds…

Model

vision-language-pretraining-study-2024

S. Kapoor

Reading notes and an experiment sketch for Vision Language Pretraining. The repository emphasizes what still needs to be tested instead of manufacturing scores or release claims. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with summary.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds, hardware, and…

Model

vision-language-pretraining-v1

Joaquín A. González

This is an exploratory note for Vision Language Pretraining. It records the intended comparison, likely confounders, and reproducibility requirements before any benchmark result is reported. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with papernotes.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds…

Model

vision-tl-action-light

Zezhiliu

轻量视觉-TL-行动线（LightTLChunk，无 VLM 骨干、约 65M 参数）的数据集与模型 checkpoint 存档。所有成功率数字均为 Panda E01 holdout 闭环 Success@K（审计协议、seed 1007、单种子）。 每个目录含 pytorchmodel.pt（LightTLChunk 权重，~65 MB）。"S@256" 为 Panda E01 holdout 128 任务闭环成功率（%，候选 256、seed 1007）；f0/f1/f2/f3 为任务族细分。 说明：checkpoint 文件名中的步数为优化器步数；以 smoke 结尾及未列出的中间快照未收录。 - 评测任务族：f0 单阶段 / f1-f3 多阶段（Panda TL 场景）。 - 数据集为 HDF5 分片格式，读取方式见训练代码（pandarenderdatasetstl loader）。

本目录是一个与官方源码隔离的实验框架。它只读使用 ILVR 的定制 Transformers 和训练类，不修改： -../../ILVR -../../mlrm-LEAD -../comt-test 本实验不使用早期的图像 two-pass 方案。原有 Monet/CoMT answer-teacher 三个实验仍只在推理时使用熵控制；新增的 CoMT/Monet Stage2 实验会在训练 rollout 中用熵决定 latent 位置，但都不加载 EMA teacher 或辅助图像。 默认评测矩阵训练两个 Monet-SFT-125K 模型： 1. monetilvr：完全使用官方 ILVR EMA teacher query。 2. monetanswerteacher：student batch 与模型 1 相同，仅在 EMA teacher 选择 helper patches 时增加标准答案表示。 另有一个独立的 comtanswerteacher 训练：只把数据切换为 CoMT，标准答案仍仅供 EMA teacher 使用，student 不可见。三个训练过程都不使用熵控制；熵控制只在训练完成后的推理/评测阶段启用。 - natural：模型自然生成 ； - entropy：高熵且满足窗口/冷却条件时，单次生成中强制 ，之后的固定 8 个 latent hidden-state feedback 继续由官方 ILVR generation loop 完成。 评测包括 VStar、HR-Bench 4K、HR-Bench 8K 和…

This PEFT adapter was trained on a 120,000-row stratified subset, not the entire training split, of Visual Jev decisions v1 at revision 687c745c34846d104ee85af802b9fd444a854f5d. It answers a task-specific question about an image with a normalized box, choice, or short text. The two published prediction logs contain the same 1,000 held-out test IDs. The 120k adapter improved all five selected-subset scores, including mean grounding IoU from 0.530 to 0.598, box choice accuracy from 94.0% to 97.5%, and spatial decision accuracy from 90.0% to 94.5%. This is not a full test-split benchmark. Modal's billing report measured $8.23 metered for the 120k staging, training, benchmark, and automatic…

This PEFT adapter was trained on a 40,000-row stratified subset, not the entire training split, of Visual Jev decisions v1 at revision 687c745c34846d104ee85af802b9fd444a854f5d. It answers a task-specific question about an image with a normalized box, choice, or short text. The GitHub composite shows selected held-out predictions with annotated photos. Its companion JSON retains full predictions. Published train and evaluation questions largely use five fixed templates. COCO instance annotations supply grounding, box choice, and left/right questions; Visual Genome v1.2 supplies selected color and relation labels. Objects, boxes, and targets vary by photo, and a photo yields only supported…

Model · Visual question answering

visual-question-answering-study

Samuel Moore

This is an exploratory note for Visual Question Answering. It records the intended comparison, likely confounders, and reproducibility requirements before any benchmark result is reported. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as VQAv2, GQA, and OK-VQA - reproducibility checks, failure modes, and open questions - topic-relevant references Start with review.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds, hardware, and raw logs. The note is…

Model · Visual question answering

visual-question-answering-warmup

Caleb JONES

A structured set of research notes on Visual Question Answering, with concrete evaluation references and open questions. Plans and hypotheses are kept separate from completed results. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as VQAv2, GQA, and OK-VQA - reproducibility checks, failure modes, and open questions - topic-relevant references Start with summary.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds, hardware, and raw logs. The note is…