AI research skills and agents

Integrated Gradients

keras-io · Kit

Shows which parts of an image drove a model's prediction, using the integrated gradients method in a Gradio page, with an elephant photo to try. For machine le…

ESPNet2 ASR Librispeech word vs bpe tokens

jkang · Kit

Compares three English speech recognition models from one ESPnet2 Conformer setup, using bpe, character and word tokens, in a Gradio page with example audio. F…

ESPNet2 ASR Librispeech Conformer (100h)

jkang · Kit

Transcribes English speech to text with an ESPnet2 Conformer model trained on 100 hours of Librispeech, in a Gradio page with example audio. For speech researc…

TFM_SimilitudSemantica_Fichero

jfarray · Kit

Compares how close in meaning texts are, using a multilingual BERT model in a Gradio page, with a sample JSON file included. For NLP students and researchers.

Zero Shot Nlp Classifier Multi Lang

iamkb · Kit

Sorts text into labels you choose, without training, across languages, using several named zero-shot models in a Gradio page. For analysts, researchers and NLP…

HF SHAP

Hellisotherpeople · Kit

Explains how text models reach their outputs with SHAP, on five named models for question answering, translation, emotion, summarization and text generation. F…

HF KeyBERT

Hellisotherpeople · Kit

Pulls keywords out of text with KeyBERT in a Streamlit page, for researchers, students and developers who want to try keyword extraction without writing code.

HF BERTopic

Hellisotherpeople · Kit

Finds topics in a collection of texts with BERTopic in a Streamlit page, for researchers and analysts who want to try topic modeling without writing code.

Qwen3.5-9B Brainwaves DeepThought STEM OneJev1.6

nightmedia · Kit

An experimental 9.4B image-and-text model made by nightmedia, a merge of three 9B models aimed at reasoning and science questions. It suits hobbyists and resea…

UniMate

Linzhan · Kit

Generates motion for skeletons of any shape, from animals to humanoids to rigged objects, from a text description. Suits animation researchers and technical ar…

Quark

FirstPrinciplesLabs · Kit

A 9B reasoning model for physics, science and maths, fine-tuned from Qwen3.5-9B by FirstPrinciples. For researchers who want step-by-step derivations and a sec…

WeVisOne-VL-2B by tencent

tencent · Kit

Reads an image with a text query and returns object boxes, points, counts, text positions and pixel masks, including alpha mattes. Suits researchers running a…

Hy-Nomas

tencent · Kit

Generates a video world one segment at a time from text instructions and camera moves, so you can change objects, style and viewpoint as it goes. For creators…

mednli_laya

pavanmantha · Kit

Checks a medical claim against a piece of evidence and answers supported, unsupported or contradicted. A fine-tuned Laya model for English research on clinical…

Sage-A1.5

InternScience · Kit

Works through long scientific tasks as an agent that delegates to subagents, checks its own progress and revises its plan. A 35B mixture-of-experts model for r…

lingbot-touch-small

robbyant · Kit

Turns tactile sensor readings from magnetic, piezoresistive and visuotactile sensors into learned features for robot manipulation. For robotics researchers who…

LingBot-Touch-Tiny

robbyant · Kit

Encodes tactile sensor signals into latent features for robot manipulation research, covering magnetic, piezoresistive and visuotactile sensing. The repo holds…

GTA world model

lucidml · Kit

Makes video from one start image while you hold keys, frame after frame, streamed to a browser. Weights and inference code for a world model trained on GTA5 ma…

Qwen3.5-0.8B-weight-space-programming by ML-Intern-lab

ML-Intern-lab · Kit

Solves math problems step by step with a small Qwen3.5-0.8B model whose weights an LLM edited directly, with no training, to stop repetition loops. For researc…

caramel-1 by naklecha

naklecha · Kit

Listens and speaks in a live back-and-forth as a 413M-parameter speech-to-speech model trained only on recordings, never on text. For voice AI researchers and…

WeVisOne-VL-4B

tencent · Kit

Finds, counts, points to, reads and segments objects in images, and makes alpha mattes, with one 4B vision-language model from Tencent. For researchers working…

Qwen3.5-4B-Qwenputer

divagr1925 · Kit

An experimental Qwen3.5-4B with a 32-bit RISC-V CPU compiled into its weights, so it does exact arithmetic inside the model. For researchers and curious develo…

Memorilla-Qwen3-8B

memorilla · Kit

Holds memory-module checkpoints for Memorilla, which add a memory to a frozen Qwen3-8B model through a Qwen3-Embedding-4B encoder. For researchers testing memo…

STRATA

nvidia · Kit

Emulates a kilometer-scale global storm-resolving atmosphere simulation with a 10-minute time step, for weather and climate research. An NVIDIA Earth-2 checkpo…

Axion-1.0-35B

Axion1-0 · Kit

A reproduction checkpoint of Axion 1.0-35B, a 35B mixture of experts model for scientific reasoning, information seeking and tool using problem solving, served…

Diffusion-Qwen3.8-27B

summerAIO · Kit

Generates text by parallel unmasking from Qwen3.8-27B converted into a masked diffusion language model. An experimental research checkpoint for researchers and…

Qwen3.5-0.8B-weight-space-programming

RikiyaT · Kit

Qwen3.5-0.8B with two weight matrices edited by an LLM, with no training, to stop its thinking loops and do better at math. An experimental model for researche…

pjit-21k

Linum-AI · Kit

Linum's experimental 2B text to image model, trained for about $21K of compute, that works best with dense 50 to 80 word prompts and cannot write text in image…

PAN 2

IFM · Kit

A 29B world model from IFM at MBZUAI that turns a scene and described actions into a video of up to 20 seconds, so an agent can preview outcomes. For researche…

qwen-concept-27b

ConceptCountry · Kit

Qwen3.8-27B with nine weight matrices edited by weight space programming, with no training, so it thinks with fewer tokens. An experimental release for researc…

Face Swap

felixrosberg · Kit

A Gradio face swapping demo from felixrosberg that runs on the FaceDancer family of models. Open it in a browser or run a copy yourself to try face swapping fo…

paper-rec

bluebalam · Kit

A Gradio demo that recommends ten recent machine learning and AI papers from arXiv, based on titles, abstracts or keywords you give it. It suits researchers an…

Deepfake Detect

artspark · Kit

A detector that tells real pictures from GAN-generated ones, using an ensemble of EfficientNet-B4 networks. It suits fact-checkers and researchers, with a Grad…

Iris-3B

speridlabs · Kit

A demo of Iris-3B, one 3B model that makes images from text, estimates depth from a single image and restores or upscales pictures. For vision researchers and…

LVBench Leaderboard

zai-org · Kit

The leaderboard page for the LVBench benchmark from zai-org, run as a Gradio app that names the LVBench dataset. For researchers who want to see how models sco…

Gpt2 Multiplication Predictor

yuntian-deng · Kit

A Gradio demo that compares GPT-2 models trained to multiply large numbers, including variants named for no reasoning steps and for reasoning steps hidden or w…

VBench Leaderboard

Vchitect · Kit

The leaderboard page for the VBench project from Vchitect, run as a Gradio app on CPU hardware. For researchers and engineers who want to see how models rank o…

Click3R

uva-cv-lab · Kit

Rebuilds a 3D scene from a pair of photos and lets you correct the result with a few clicks that mark the same point in both views. A research demo for compute…

Laya Vision

thaitea · Kit

Answers yes/no, multiple-choice and rubric-scored questions about an image in a single pass, with no text generation. It runs a small 201M checkpoint on a CPU…

Paper Pulse

tardellirs · Kit

Shows the day-by-day upvote history of every Hugging Face Daily Paper since March 2024, with each paper's daily rank and the labs and authors behind the top on…

Free-View Expressive Talking Head Video Editing

sky24h · Kit

A Gradio demo for editing talking head videos, with free viewpoint and expressive control as its title says. For researchers and developers who want to try the…

HockeyRink

SimulaMet-HOST · Kit

Finds 56 landmark points on an ice hockey rink in a picture and draws them with IDs and confidence scores. Built for sports analysts, broadcast graphics teams…

Arabic LLM Leaderboard - Broad (ABL)

silma-ai · Kit

Ranks language models on an Arabic benchmark in a Gradio leaderboard, with code you can adapt to host your own board. Suits Arabic NLP researchers and teams co…

JLD Perceptual Distance

shreshthsaini · Kit

Scores how different a distorted image looks from its reference, with a lens overlay showing where. For image quality researchers who want to try the JLD metri…

Rabbit Pain Identifier

sheildo · Kit

Screens a single rabbit photo for signs of pain by measuring 23 facial landmarks and labelling it Relaxed or Pain with a probability. A research prototype for…

ModelScope Text To Video

shamedrank10 · Kit

Turns an English text prompt into a short 256x256 video clip with the ModelScope text-to-video diffusion model, in a Gradio demo. For researchers and curious m…

GIFT Eval

Salesforce · Kit

The Salesforce page for GIFT-Eval, a benchmark for general time series forecasting. Its repository holds a results folder and the app code. Suits forecasting r…

MoGe 2

Ruicheng · Kit

Estimates the geometry of a scene at true scale from a single image, in a Gradio demo you open in the browser. Suits researchers and developers working with de…

TIME Benchmark Leaderboard

Real-TSF · Kit

A leaderboard for the TIME benchmark of probabilistic time series forecasting, with overall scores, per-dataset breakdowns and test window plots. Suits forecas…

Colpali

rayyan0 · Kit

A Gradio demo of the vidore ColPali v1.3 model, shipped with a stored file of page embeddings. For developers and researchers trying out visual document retrie…