Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Paper • 2606.30616 • Published • 69
Stoney Kang
sikang99
AI & ML interests
Remote Control based on Vision
Recent Activity
upvoted a paper about 1 hour ago
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent upvoted a paper about 1 hour ago
One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models upvoted a paper about 6 hours ago
Agentic Abstention: Do Agents Know When to Stop Instead of Act?Organizations
upvoted 2
papers about 1 hour ago
upvoted 3
papers about 6 hours ago
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
Paper • 2606.28733 • Published • 123
One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications
Paper • 2606.25621 • Published • 16
OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
Paper • 2606.29537 • Published • 15
upvoted 8
papers about 21 hours ago
Autodata: An agentic data scientist to create high quality synthetic data
Paper • 2606.25996 • Published • 18
DanceOPD: On-Policy Generative Field Distillation
Paper • 2606.27377 • Published • 80
OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
Paper • 2606.26790 • Published • 52
Vesta: A Generalist Embodied Reasoning Model
Paper • 2606.20905 • Published • 9
Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System
Paper • 2606.18112 • Published • 22
Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
Paper • 2606.17846 • Published • 23
Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting
Paper • 2606.30017 • Published • 16
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
Paper • 2606.28128 • Published • 45
upvoted 3
papers 2 days ago
upvoted a paper 5 days ago
upvoted 3
papers 6 days ago