view article Article DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models 5 days ago • 32
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation Paper • 2604.18168 • Published 7 days ago • 96
view article Article How to Ground a Korean AI Agent in Real Demographics with Synthetic Personas 6 days ago • 24
How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data Paper • 2604.14164 • Published Mar 23 • 34
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper • 2604.14268 • Published 12 days ago • 112
view article Article Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion 12 days ago • 12
view article Article "Darwin-27B-Opus: Surpassing the Foundation Model Without Training" 14 days ago • 12
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents Paper • 2604.07430 • Published 19 days ago • 186
ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 18 days ago • 259
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published 18 days ago • 285
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 19 days ago • 321
WildDet3D: Scaling Promptable 3D Detection in the Wild Paper • 2604.08626 • Published 18 days ago • 240
view article Article BidirLM: Turning Generative LLMs into the Best Open-Source Omnimodal Encoders 19 days ago • 26
Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision Paper • 2604.04934 • Published 21 days ago • 45