view post Post 21 imagine the text editting capabilities of gpt 5 nano on a model with less than 100m parameters... 🏃🏽♂️💨 See translation Reply
HumanNet: Scaling Human-centric Video Learning to One Million Hours Paper • 2605.06747 • Published 5 days ago • 41
InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search Paper • 2605.07510 • Published 4 days ago • 5
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation Paper • 2605.08029 • Published 4 days ago • 9
Aryabhata: An exam-focused language model for JEE Math Paper • 2508.08665 • Published Aug 12, 2025 • 16
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling Paper • 2605.05922 • Published 5 days ago • 3
SkillOS: Learning Skill Curation for Self-Evolving Agents Paper • 2605.06614 • Published 5 days ago • 37
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Paper • 2605.06130 • Published 5 days ago • 68
AI Co-Mathematician: Accelerating Mathematicians with Agentic AI Paper • 2605.06651 • Published 5 days ago • 12
Lightning Unified Video Editing via In-Context Sparse Attention Paper • 2605.04569 • Published 6 days ago • 15
Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation Paper • 2605.04128 • Published 7 days ago • 15
A Benchmark for Interactive World Models with a Unified Action Generation Framework Paper • 2605.03941 • Published 7 days ago • 5
Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies Paper • 2605.03596 • Published 7 days ago • 7
OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories Paper • 2605.04036 • Published 7 days ago • 64
SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment Paper • 2605.04012 • Published 7 days ago • 11
Motion-Aware Caching for Efficient Autoregressive Video Generation Paper • 2605.01725 • Published 9 days ago • 8