Aamer Mihaysi
O96a
AI & ML interests
Ethical AI, NLP & Cognitive architectures
Recent Activity
commentedon a paper about 19 hours ago
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling commentedon a paper 2 days ago
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation commentedon a paper 3 days ago
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing PredictionOrganizations
spaces 56
Build error
Agents
MMSkills Demo - Multimodal Skill Retrieval for Visual Agents
🤖
Build error
Agents
MMSkills Demo - Multimodal Skill Retrieval for Visual Agents
🤖
Sleeping
Agents
FEST-Style Few-Shot RL for Reasoning
🧠
Solve math problems with step‑by‑step reasoning
Runtime error
Agents
FEST-Style Few-Shot RL for Reasoning
🧠
Runtime error
Agents
Exp-007: Multi-Agent Pathfinding with Communication
🤖
Sleeping
Agents
Implicit Memory Conflict Validator
🧠
Evaluate LLM responses for outdated memory conflicts