Victor Mustar's picture

Building on HF

Victor Mustar PRO

victor

huggingface

·

victormustar

AI & ML interests

Building the UX of this website

Recent Activity

liked a model about 9 hours ago

Kwai-Keye/Keye-VL-2.0-30B-A3B-GGUF

liked a model about 10 hours ago

Playtime-AI/LTX-2.3-Ted

reacted to Jaward's post with 🔥 about 10 hours ago

Our preprint is out! We attempt to model human teaching behaviors into agents yielding a unified framework that enables adaptive personalized learning experiences: LectūraAgents addresses the prevailing limitations in current AI learning systems with three essential capabilities: (1) a hierarchical multi-agent architecture modeled on academic standards. we observe that agents collaborating across hierarchies yield better learning outcomes. (2) an adaptive embodied teaching mechanism, in which the instructor agent executes visible and pedagogically motivated teaching actions (e.g. handwrite, highlight, circle etc) on contents in a teaching environment while speaking. (3) to achieve this we propose a novel teaching action-speech alignment algorithm (TASA) that dynamically aligns speech with visual teaching actions: specifically, TASA temporally chops up speech segments into word-level tokens, performs salience heuristics analysis on learning contents (texts, images etc) then identifies relevant regions to apply pedagogical teaching actions that guide attention and augment understanding. We conducted several experiments to assess these capabilities: starting with pedagogical evaluation of the various components under frontier models, comparative analysis with existing frameworks and an efficacy study with real students. Results show consistent gains in standard instructional metrics (curated by expert educators) spanning lecture content quality, embodied teaching quality, assessment, and personalization over baseline systems, positioning LectūraAgents as a pedagogically well-grounded framework for personalized learning at scale. Paper: https://huggingface.co/papers/2606.16428 Data: https://huggingface.co/datasets/Jaward/lectura-agents-data

View all activity

Organizations

victor 's Spaces 84

EDGERUNNERS

Play a fast‑paced parkour game in your browser

Claude World Cup 2026 Pronostic Wallchart

All 104 World Cup 2026 matches predicted by Claude agents

Fable 5 Boeing 747

Procedural Boeing 747-400 in Three.js, built by Fable 5

Nemotron 3.5 ASR Streaming

Multilingual streaming ASR with NeMo

Fleurs de France

A 3D Gaussian-splat garden of French flowers

Opus 4.8 Boeing 747

Explore a 3D Boeing 747 model in your browser

DreamVerse FastVideo ZeroGPU

FastVideo DreamVerse continuation demo for ZeroGPU

LongCat-Video-Avatar 1.5

Audio-driven talking-head video generation (Meituan LongCat)

DeepSite

Imagine and Share in 1-Click

FLUX.2-dev

Generate images from text prompts

Pixal3D Studio

Clean image-to-3D studio for Pixal3D

Lance Multitask ZeroGPU

Multitask ZeroGPU demo for ByteDance Lance

MTP Bench Viz

Compare LLM decoding speeds with and without MTP

MTP on HF Inference Endpoints

Speed up LLM text generation with speculative decoding

canirun.ai minimal

Score AI model compatibility with your hardware

Just Bash MCP

Remote MCP server exposing just-bash as an agent sandbox

Hugging Face on Hacker News

Visualizing HF mentions and engagement on HN over time

ace-step-jam

Describe any song — AI writes & produces it

3D Horse

View a 3D horse generated from a text prompt

MOSS-TTS-Nano

0.1B multilingual TTS with voice cloning

Car Game

Play a fast 3D car racing game

Front Skill Bakeoff

Browse generated landing page demos from different frontend skills

Z-Image Studio

Minimalist AI image studio powered by Z-Image Turbo

DLSS 5 Anything

Turn any image into a DLSS 5 meme (using FLUX.2-klein-9b-kv)