AgentDoG 1.5 A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
@_akhaliq
-
Generative Supervision for Embodied Intelligence
By
–
GEM
— AK (@_akhaliq) 28 mai 2026
Generative Supervision Helps Embodied Intelligence pic.twitter.com/IlGPbxkwHSGEM Generative Supervision Helps Embodied Intelligence
-
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
By
–
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
-
ProRL: Reinforcement Learning for Proactive Recommendations
By
–
ProRL Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
-
Masked Region Transformer for Layered Image Generation
By
–
MRT Masked Region Transformer for Layered Image Generation and Editing at Scale
-
Contrastive Distribution Matching for Sequential Monte Carlo Diffusion
By
–
Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
-
Gamma-World: Generative Multi-Agent World Modeling
By
–
Gamma-World
— AK (@_akhaliq) 28 mai 2026
Generative Multi-Agent World Modeling Beyond Two Players pic.twitter.com/YxHI13Qsl9Gamma-World Generative Multi-Agent World Modeling Beyond Two Players
-
Mix-Quant: Quantized Prefilling and Decoding for Agentic LLMs
By
–
Mix-Quant Quantized Prefilling, Precise Decoding for Agentic LLMs
-
Evaluating Memory in Long-Horizon AI Agent Systems
By
–
LongMINT Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
-
ESI-Bench: Towards Embodied Spatial Intelligence and Perception-Action Loops
By
–
ESI-Bench Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop