Open-Weight Models Under Creative Commons Attribution 4.0

Model

3d-scene-understanding

Coco Wijaya

This repository contains a working research note about 3D Scene Understanding. It organizes motivation, related work, a falsifiable hypothesis, and an evaluation plan. It is not presented as a completed paper or a release of trained models. - 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…

Adaptive Geometry-Aware Fourier Neural Operator — with the complete controlled-evidence stack, extended depth sweep to 16, a second PDE family, a deformation baseline, a direct measurement of geometric forgetting, and a fully programmatic research paper (paper/agfnopaper.pdf). (mode truncation discards everything above the cut). A zero-gated, SDF-derived multiplicative modulation of the spectral weights restores the truncated band by spectral convolution — and the paper measures the whole story: diagnosis (proposition), fix (mechanism), consequence (probe). = 0.971× FNO's global error — the gain is NOT extra parameters (5.10M vs 4.81M) or channels (identical 3-channel inputs). −56% ring.…

Model

amtflow

Vaclis

Model assets for AMTFlow, a modular instrument-conditioned automatic music transcription pipeline (instrument tagging → instrument-family routing → MuScriptor). AMTFlow downloads these files on first use; you do not need to fetch them by hand. One classification head per frozen audio encoder, trained on OpenMIC-2018 (20 instrument classes). AMTFlow's probe tagger runs the encoder, applies the head to one layer's time-averaged features, and marks an instrument family present when any of its classes reaches that class's threshold. Several taggers, including audio-language models, can be combined by union or majority vote. Test mAP is the mean over five probe seeds with a 95% t-interval over…

Model

assignment-contrastive-learning50

Kelvin Takahasi

Reading notes and an experiment sketch for Contrastive Learning. 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 reading.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…

atomizer on GLiNER small v2.5 (gliner-community/glinersmall-v2.5): a single-pass span atomizer with a critic. It splits a text into short, self-contained claims ("atoms") and scores - verifiable: is this a factual claim that can be checked? - checkworthy: is it worth fact-checking? Atomization is the step any claim-level fact-checking tool depends on: search, evidence judgment and the verdict all work on the claims it produces, so a claim that is missed, merged or wrongly resolved here cannot be checked correctly later. The figure shows fact-assessor, our own opinionated fact-assessment tool: atomizer is the "trained atomizer" option of its Atomization step, and its verifiable / checkworthy…

atomizer on Fastino's GLiNER2.5 base (fastino/gliner2.5-base-v1) with atomizer's standard heads: a single-pass span atomizer with a critic. It splits a text into short, self-contained claims ("atoms") and scores each one for verifiable (is it a checkable factual claim) and checkworthy (is it worth checking). 202M parameters. The model does not generate text. It selects words from the input, replaces references ("She" → "Marie Curie") with earlier spans or keeps them as written, and adds closed-class glue words ("is", "the", "'s"). An atom cannot contain a name or number that is not in the input. One repo per architecture. The atomizer models live in one Hugging Face repo per backbone and…

atomizer on Fastino's GLiNER2.5 base (fastino/gliner2.5-base-v1) with its native heads: a single-pass span atomizer with a critic. It splits a text into short, self-contained claims ("atoms") and scores each one for verifiable (is it a checkable factual claim) and checkworthy (is it worth checking). 192M parameters, ~10 ms per text on a GPU, 60–70 ms on a laptop CPU. The model does not generate text. It selects words from the input, replaces references ("She" → "Marie Curie") with earlier spans or keeps them as written, and adds closed-class glue words ("is", "the", "'s"). An atom cannot contain a name or number that is not in the input. One repo per architecture. The atomizer models live…

atomizer on Fastino's GLiNER2.5 base (fastino/gliner2.5-base-v1) with a head-interaction block ("xhead"): a single-pass span atomizer with a critic. It splits a text into short, self-contained claims ("atoms") and scores each one for verifiable (is it a checkable factual claim) and checkworthy (is it worth checking). 217M parameters; ~1.5× slower than the small model. The model does not generate text. It selects words from the input, replaces references ("She" → "Marie Curie") with earlier spans or keeps them as written, and adds closed-class glue words ("is", "the", "'s"). An atom cannot contain a name or number that is not in the input. One repo per architecture. The atomizer models live…

Model · Image classification

BedNet

Adamgoza

Binary image classifier that answers one question from a fixed bed-camera view: is there a printed object on the print bed? Built for autonomous 3D-print-farm fulfillment (auto-releasing completed prints without a human looking at every camera frame). Live inference on frames from two printers never seen during training. Banner shows the model's actual output: ~1,200 frames from 29 farm printers. Labels derived from operational events and then manually audited by the operator (7 corrections applied via a review tool): Convention: clear means a clean bed — filament scraps and debris count as occupied. Split is group-aware (all frames from one printer/camera go to exactly one split), so test…

This Hugging Face repository hosts the released LoRA checkpoints for CapField-OPD, an on-policy distillation (OPD) framework that consolidates multiple reward-specialized teachers into a single student through a continuous capability field. Existing multi-teacher OPD methods route each prompt to a single teacher according to its semantic category, implicitly binding the desired capability to prompt content. CapField-OPD instead conditions the student on an explicit capability coordinate $\boldsymbol{\lambda} \in [0,1]^K$, whose axes control the strength of each capability. The base model, single-capability teachers, and joint-capability teachers serve as anchors of the field, and their…

An unchanged copy of istupakov/parakeet-tdt-0.6b-v3-onnx at commit 8f23f0c03c8761650bdb5b40aaf3e40d2c15f1ce, kept so the Capset caption panel for After Effects downloads from a source that cannot change under it. Parakeet TDT 0.6B v3 by NVIDIA, exported to ONNX by istupakov. Original model: nvidia/parakeet-tdt-0.6b-v3. Licence: CC-BY-4.0 (https://creativecommons.org/licenses/by/4.0/), the same as the original. No file here has been modified; the original model card is kept as UPSTREAM-README.md.

Model · Audio to audio

chatterbox-s3gen-vc-grow-ce-continue

LAION eV

This is a research-stage audio-to-audio voice-conversion adapter, not a standalone TTS model. It changes Chatterbox's S3Gen acoustic decoder while keeping the S3 semantic tokenizer, CAMPPlus speaker encoder and HiFT vocoder frozen. The adapter is rank 128 on 224 q/k/v/out attention projections, with the previously trained 99-score conditioning projector. Download the pinned upstream Chatterbox S3Gen and the 300-hour supervised/v1 RL parent release separately. This repository does not contain the upstream base weights or the training audio. The completed v1 continue rank-128 adapter at step 4,000 is continued without merging it into the base. The reward uses the frozen model at revision…

Model · Audio to audio

chatterbox-s3gen-vc-grow-ce-remerged

LAION eV

This is a research-stage audio-to-audio voice-conversion adapter, not a standalone TTS model. It changes Chatterbox's S3Gen acoustic decoder while keeping the S3 semantic tokenizer, CAMPPlus speaker encoder and HiFT vocoder frozen. The adapter is rank 128 on 224 q/k/v/out attention projections, with the previously trained 99-score conditioning projector. Download the pinned upstream Chatterbox S3Gen and the 300-hour supervised/v1 RL parent release separately. This repository does not contain the upstream base weights or the training audio. The completed v1 mergednew step-4,000 adapter is merged into its effective base and a new rank-128 adapter is initialized for this follow-up. The reward…

Model · Audio to audio

chatterbox-s3gen-vc-grow-ce-speaker

LAION eV

This is a research-stage audio-to-audio voice-conversion adapter, not a standalone TTS model. It changes Chatterbox's S3Gen acoustic decoder while keeping the S3 semantic tokenizer, CAMPPlus speaker encoder and HiFT vocoder frozen. The adapter is rank 128 on 224 q/k/v/out attention projections, with the previously trained 99-score conditioning projector. Download the pinned upstream Chatterbox S3Gen and the 300-hour supervised/v1 RL parent release separately. This repository does not contain the upstream base weights or the training audio. The completed v1 continue rank-128 adapter at step 4,000 is continued, now with an explicit target-speaker reward. The reward uses the frozen model at…

This repository contains the CI-Net processing, training, inference, and validation code. The directories under code follow the processing order: 1. datapreparing: read and align satellite and radar inputs. 2. labeling: create cloud labels. 3. finalpreprocess: convert the prepared fields into model input files. 4. training: train the model and run inference. 5. validation: create validation targets and calculate validation metrics. Each code directory contains Python files in src and its configuration and shell entry points in run. rawdata contains the input example included with this repository. result contains prepared data, model files, inference outputs, and validation outputs. See…

Model

community-1-diarization-coreml

Onemira

Pinned, byte-preserving mirror of the assets used by OneMira's offline speaker-label worker. Original Community-1 models: pyannote/speaker-diarization-community-1, pyannote contributors, CC BY 4.0. Core ML conversion: FluidInference/speaker-diarization-coreml, revision 1ed7a662fdc7109e36d822db793ee6eebdaf8594. The converted embedding graph exposes raw features before L2 normalization so OneMira can preserve the upstream PLDA centering semantics. No weight training or model upgrade is included. SOURCE.json records upstream provenance and every artifact size/SHA-256. NOTICE.txt includes attribution and license text, including the Apache-2.0 notice for the native FluidAudio pipeline. The…

Model · Feature extraction

continuous-mimi-onnx

MaAI

This is a modified ONNX export of the Mimi audio codec encoder. It bypasses the Residual Vector Quantization (RVQ) to directly output continuous feature representations instead of discrete tokens. This preserves fine-grained acoustic details, making it ideal for downstream tasks like real-time dialogue analysis or speech emotion recognition. This model is a derivative work based on the "Mimi" model. Numbers below are illustrative (desktop CPU, FP32 ONNX vs PyTorch kyutai/mimi, streaming chunk emit=1280 @ 16 kHz, inference.py --compare). Your machine, thread counts, and ORT / PyTorch builds will shift them. Speed — RTF (processing time ÷ real-time audio length per chunk) In repeated 1-second…

Model

cross-modal-fusion-int8

Destiny Clark

This is an exploratory note for Cross Modal Fusion. 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

cs224n-ocr-freeform

Olivia K. Taylor

This is an exploratory note for OCR Freeform. 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 FUNSD, SROIE, and CORD - reproducibility checks, failure modes, and open questions - topic-relevant references Start with analysis.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 intentionally…

Model

data-efficient-learning-playground20

Swati

A structured set of research notes on Data Efficient Learning, 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 analysis.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…

Model

data-efficient-learning-small-2023

Hoangnam Tran

Reading notes and an experiment sketch for Data Efficient Learning. 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 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, hardware, and…

Model

document-ai-pretrained

Subramaniankabir

This is an exploratory note for Document AI. 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 FUNSD, SROIE, and CORD - 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, hardware, and raw logs. The note is intentionally…

Model

document-ai-survey

Chunyu

This is an exploratory note for Document AI. 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 FUNSD, SROIE, and CORD - 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, hardware, and raw logs. The note is intentionally…

Model

ecommerce-churn-ltv-models

Kicaulah

Production-grade machine learning models for customer churn risk classification (forward 90-day inactivity) and customer lifetime value (LTV) regression (forward 180-day net spend), trained on the validated UCI Online Retail II dataset. - Models were validated using strict temporal cohort splits across monthly cutoff dates (2010-03-01 through 2011-06-01). - Random K-fold splitting was strictly avoided to prevent temporal leakage and lookahead bias. Using cost-benefit scenario analysis on test cohort ($N=4,324$): - Unit Contact Cost ($c$): £2.50 - Retention Offer / Incentive ($d$): £15.00 - Customer Lifetime Value Recovered ($v$): £45.00 - Uplift / Success Rate ($u$): 15% (Base Scenario) The…

Model

embodied-ai-tryout6

Chiahao Lee

This is an exploratory note for Embodied AI. 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 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…

Model · Object detection

factory-safety-isaac-yolo

Intelligence Big Data Processing Laboratory

YOLO weights for factory-safety-isaac — a body-camera-only factory safety agent built on NVIDIA Isaac Sim. These are the two trained detection models the project uses; no other model files are hosted here (MediaPipe's hand landmarker and the Qwen2.5-7B LLM are pulled from their own upstream sources at first run, see the project README). on 7,700 synthetic images generated in Isaac Sim (Replicator auto-labeling), 70% bodycam / 30% free-viewpoint. Or with the project's own scripts (scripts/runpatrol.py --weights, scripts/runpatrol.py --pinch-weights ). Trained entirely on synthetic data (NVIDIA Isaac Sim warehouse assets + Poly Haven CC0 tool scans). See the main repository for full…

Model · Text to speech

Fatiman-TTS-v1

Jean Sauvenel Beaudry

A Haitian Creole (Kreyòl) text-to-speech model: Kyutai's Pocket TTS (French 24-layer model) fine-tuned on Kreyòl speech. It runs on a CPU and streams: the first audio arrives in about 0.12 s on a laptop. It is the voice of Klara, a Kreyòl voice assistant that runs offline. 80 held-out Kreyòl sentences (none in training), read aloud and transcribed back by two speech recognizers; character error rate, lower is better. The French model already reads Kreyòl at about 20% CER (its errors are French spelling habits, silent final letters above all); the fine-tune keeps its tokenizer and text embedding and teaches it Kreyòl spelling. Nine Kreyòl voices come with the model, in voices/. Each was made…

Model

few-shot-multimodal-study

Rajesh T. Singh

Reading notes and an experiment sketch for Few Shot Multimodal. 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 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, hardware, and raw…

Model

few-shot-multimodal-tutorial

Lucas

This is an exploratory note for Few Shot Multimodal. 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 reading.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…

This compact model screens aerial tiles for potential flood inundation. It was selected from cleared regional calibration trials using the published audit rule. Use the bundled INT8 ONNX graph with the included land-cover labels and tile-normalization settings.

ONNX int8 export of kyutai/pocket-tts, six bundles (german2026-10, english2026-09, french2026-10, italian2026-10, spanish2026-10, portuguese2026-10). Source: kyutai/pocket-tts @ 3e82814a68665eec246ff649b14c71331f955c06 (languages/ /model.safetensors). The model weights are © Kyutai Labs, licensed under CC BY 4.0 (inherited from kyutai/pocket-tts). The ONNX conversion and the quantization are the only changes. Please credit Kyutai Labs when you use these files.

Working draft v6 (2026-10-07), experimental technical report, not peer reviewed. The roughly twofold joint-KL ratio in §5.7 is a provisional result while a matched-denominator recheck finishes; other numbers may still change. kev-d3-paper-draft-v6.pdf (current) Per-module sub-3-bit sensitivity of two Qwen3.5 hybrid decision models (Gated DeltaNet linear attention interleaved 3:1 with full attention), measured as option-distribution KL under binary / ternary / 3-bit / 4-bit GPTQ, with a multiple-choice knapsack priced in the target runtime's storage format (HyBitQ) that turns the measurements into bit allocations. Related release: Jakevin/kev-4b-ternary-mlx (revision v2.0 uses this…

A from-scratch hybrid OCR pipeline for the saeidseyfi/khattat dataset, built by saeidseyfi from 100% free, offline components — no training required, no paid APIs. 1. OpenCV preprocessing — upscale, Otsu/adaptive binarization, deskew, morphology 2. EasyOCR (fa+ar+en) — CRAFT detection + CRNN recognition 3. Tesseract 5 (tessdatabest: fas / ara / eng) — LSTM models with word confidences 4. Confidence ensemble — script detection + weighted candidate selection + language normalization 5. pix2tex (LaTeX-OCR) for math formulas — ViT -> LaTeX + math-token candidate scoring 6. OpenCV contour classification for hand-drawn shapes (10 classes) 7. Caption OCR — first ink cluster below the shape -> en…

Handwritten line recognizer for Persian / Arabic / English text plus math symbols, fine-tuned on the saeidseyfi/khattat dataset (line crops, input 32x256, max 88 label chars). CPU (2-core) budget fine-tune; decoder+head trained, STR backbone frozen The training pipeline is time-budgeted and fully resumable — continuing on a GPU with the same script converges substantially further. - best.pt -- model checkpoint (state dict + vocab) - vocab.txt -- 176-char vocabulary (fa / ar / en / digits / math) - demokhattatparseq.mp4 -- demo: test lines, ground truth vs prediction - evalreport.json, log.txt, worstsamples.json -- metrics

Model

knowledge-distillation-2024

Truong Bryan

Reading notes and an experiment sketch for Knowledge Distillation. 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 raw…

Model

ml-knowledge-distillation

Lv Yuxuan

This is an exploratory note for Knowledge Distillation. 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 notes.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…

Model · Image classification

mmfm-breast-imaging-checkpoints

NFadlallah

ResNet-18 binary (benign vs. malignant) classification checkpoints, trained per-dataset on eight public breast-imaging sources spanning ultrasound, Full write-up, methodology, and comparison to each source paper's own These are single-modality baselines, not the 3-branch fusion model. Each checkpoint is models.SingleBackboneClassifier (one ResNet-18 backbone, ImageNet-pretrained, first conv adapted for non-RGB inputs where applicable) — see models/backbone.py / training/train.py in the repo for the loading code. For the 5-fold datasets, this is one fold's checkpoint, not an ensemble or the averaged model — reported accuracy is the 5-fold mean from the full report for context, not this…

Model

multimodal-reasoning-base

Jonas W. Schmidt

A structured set of research notes on Multimodal Reasoning, 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 NLVR2 - 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 intentionally…

Model

my-embodied-ai

Marcin Nowak

This is an exploratory note for Embodied AI. 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 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…

Model

neural-architecture-search-int4

Do-yun Lee

Reading notes and an experiment sketch for Neural Architecture Search. 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

neural-architecture-search-study

David Okoro

This is an exploratory note for Neural Architecture Search. 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 notes.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

notes-grounded-language

Magdalena Szymanski

This is an exploratory note for Grounded Language. 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 RefCOCO, Flickr30k, and Visual Genome - 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, hardware, and raw logs. The…

Model

notes-multimodal-generation

Kevin Sitorus

This repository contains a working research note about Multimodal Generation. It organizes motivation, related work, a falsifiable hypothesis, and an evaluation plan. It is not presented as a completed paper or a release of trained models. - 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…

Model

notes-zero-shot-transfer

Piotr-Kowalski

Reading notes and an experiment sketch for Zero Shot Transfer. 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 analysis.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…

Model

ocr-freeform-test

Jungkookjeon1994

This repository contains a working research note about OCR Freeform. It organizes motivation, related work, a falsifiable hypothesis, and an evaluation plan. It is not presented as a completed paper or a release of trained models. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as FUNSD, SROIE, and CORD - reproducibility checks, failure modes, and open questions - topic-relevant references Start with analysis.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…