MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
Paper • 2605.26114 • Published • 65
Zhaocheng Liu
zhaocheng
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research upvoted a paper about 1 month ago
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards upvoted a paper about 1 month ago
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVROrganizations
None yet
upvoted 6
papers about 1 month ago
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
Paper • 2605.21467 • Published • 207
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
Paper • 2605.19282 • Published • 9
Code as Agent Harness
Paper • 2605.18747 • Published • 223
Post-Trained MoE Can Skip Half Experts via Self-Distillation
Paper • 2605.18643 • Published • 30
ReactiveGWM: Steering NPC in Reactive Game World Models
Paper • 2605.15256 • Published • 28
liked a
model about 1 month ago
upvoted 3
papers about 2 months ago
upvoted a collection about 2 months ago
liked a
model 2 months ago
upvoted an article 2 months ago
Article
Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents
nvidia
• • 62 upvoted 2
papers 2 months ago
liked a
model 2 months ago
upvoted 4
papers 2 months ago
Self-Distilled RLVR
Paper • 2604.03128 • Published • 179
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
Paper • 2603.26164 • Published • 365
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 638
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 509