LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
Paper • 2509.14252 • Published • 5 •
1
Librarian Bot (Bot)
librarian-bot
AI & ML interests
I am a friendly librarian bot working to help improve metadata on the 🤗 hub. Run by Hugging Face'ss Machine Learning Librarian (HF username: davanstrien)
Recent Activity
new activity about 1 hour ago
vengal78/items_prompts_lite:Librarian Bot: Add language metadata for dataset new activity about 21 hours ago
librarian-bots/dataset-to-model-monitor:Discussion tracking new models trained on google/fleurs commentedon a paper about 22 hours ago
LLM-JEPA: Large Language Models Meet Joint Embedding Predictive
ArchitecturesOrganizations
Librarian Bot: Add language metadata for dataset
#2 opened about 1 hour ago
by librarian-bot
Discussion tracking new models trained on google/fleurs
320
#6 opened over 2 years ago
by 
librarian-bot
commented a
paper about 22 hours ago
Librarian Bot: Add language metadata for dataset
#2 opened 1 day ago
by librarian-bot
commented 16
papers 1 day ago
T5Gemma-TTS Technical Report
Paper • 2604.01760 • Published • 5 •
2
DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data
Paper • 2604.01666 • Published • 7 •
2
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
Paper • 2604.01007 • Published • 19 •
2
GPA: Learning GUI Process Automation from Demonstrations
Paper • 2604.01676 • Published • 9 •
2
Woosh: A Sound Effects Foundation Model
Paper • 2604.01929 • Published • 4 •
3
Executing as You Generate: Hiding Execution Latency in LLM Code Generation
Paper • 2604.00491 • Published • 3 •
2
Generative World Renderer
Paper • 2604.02329 • Published • 86 •
3
ASI-Evolve: AI Accelerates AI
Paper • 2603.29640 • Published • 18 •
2
FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition
Paper • 2604.02088 • Published • 5 •
2
Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers
Paper • 2603.27666 • Published • 14 •
3
Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time
Paper • 2604.00917 • Published • 12 •
2
AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation
Paper • 2603.28068 • Published • 9 •
2
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
Paper • 2603.26164 • Published • 153 •
4
Forecasting Supply Chain Disruptions with Foresight Learning
Paper • 2604.01298 • Published • 5 •
2
LinguDistill: Recovering Linguistic Ability in Vision- Language Models via Selective Cross-Modal Distillation
Paper • 2604.00829 • Published • 5 •
2
AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration
Paper • 2604.01014 • Published • 7 •
2