taesiri PRO
taesiri
AI & ML interests
AGI ... one linear layer at a time
Recent Activity
submitted a paper about 8 hours ago
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding submitted a paper about 8 hours ago
Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising submitted a paper about 8 hours ago
ClawGym: A Scalable Framework for Building Effective Claw Agents