NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale
Paper • 2611.02102 • Published • 32
Ayaka Nishimura
ayakani
·
AI & ML interests
anomaly detection
multi-agent RL
reward hacking
Recent Activity
upvoted a paper about 10 hours ago
NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale upvoted a paper about 10 hours ago
Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer upvoted a paper 1 day ago
CaPtain: A Pipeline for Post-Training Code-as-Policy Robot AgentsOrganizations
None yet
upvoted 2
papers about 10 hours ago
upvoted 3
papers 1 day ago
CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents
Paper • 2610.40799 • Published • 21
On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning
Paper • 2610.40945 • Published • 12
Probing Spatial State Representations in Visual Foundation Models
Paper • 2610.40636 • Published • 21
upvoted a paper 3 days ago
upvoted 8
papers 4 days ago
Generalized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding
Paper • 2610.29552 • Published • 5
AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents
Paper • 2610.22684 • Published • 5
Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players
Paper • 2610.33845 • Published • 19
MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation
Paper • 2610.23234 • Published • 11
RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation
Paper • 2610.27782 • Published • 5
DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning
Paper • 2610.32093 • Published • 19
miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning
Paper • 2610.23928 • Published • 15
HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience
Paper • 2610.34186 • Published • 5
upvoted 6
papers 5 days ago
Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models
Paper • 2610.30435 • Published • 7
Learning and Reasoning with Geometry: How Generation Helps Spatial Understanding
Paper • 2610.36022 • Published • 7
OvisOCR3 Technical Report
Paper • 2610.33066 • Published • 30
What Outcome RL Buys: Finishing, Reliability, Rarely Reach
Paper • 2610.34894 • Published • 6
S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning
Paper • 2610.35518 • Published • 18
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
Paper • 2610.37666 • Published • 59