view article Article Welcome EmbeddingGemma, Google's new efficient embedding model By tomaarsen and 5 others • 1 day ago • 46
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning Paper • 2509.02479 • Published 2 days ago • 74
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use Paper • 2509.01055 • Published 4 days ago • 53
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning Paper • 2509.02544 • Published 2 days ago • 95
Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR Paper • 2509.02522 • Published 2 days ago • 21
Running 2 2 Entropy Harvester 🌍 Analyze CSV data to understand its structure and get optimization recommendations
MobileCLIP Models + DataCompDR Data Collection MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models. • 25 items • Updated 9 days ago • 34
Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Paper • 2508.21365 • Published 7 days ago • 21
AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications Paper • 2508.16279 • Published 14 days ago • 22
Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD Paper • 2508.17450 • Published 11 days ago • 8
ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models Paper • 2508.18773 • Published 10 days ago • 14