SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs
Paper • 2610.31062 • Published • 15 •
8
Guilherme Monteiro
guicybercode
AI & ML interests
smol-llms, llm-training, chinese-history, brazilian-history, production-ml, terminal-ui, data-curation, edge-ai
Recent Activity
new activity about 2 hours ago
jmrenouard/microllm-guardrail-int8:Prompt-injection rubric on Portuguese input commentedon a paper 1 day ago
SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs commentedon a paper 1 day ago
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing PredictionOrganizations
Prompt-injection rubric on Portuguese input
2
#1 opened 2 days ago
by guicybercode
commented 4
papers 1 day ago
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
Paper • 2609.18063 • Published • 30 •
9
Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
Paper • 2610.30755 • Published • 23 •
8
SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs
Paper • 2610.31062 • Published • 15 •
8
Task instructions as the hardest benign subset
2
#2 opened 5 days ago
by guicybercode
commented 2
papers 2 days ago
upvoted 2
papers 2 days ago
liked a
model 2 days ago
liked a
dataset 2 days ago
liked a
model 2 days ago
Voices in pt_audio and Brazilian speaking rate
#1 opened 2 days ago
by guicybercode
Sample size behind the 6.35% WER and the fp32 baseline
#1 opened 2 days ago
by guicybercode
commented a
paper 3 days ago
Per-language false alarms and the int8 ONNX file on long inputs
3
#1 opened 3 days ago
by guicybercode
updated 3
Spaces 3 days ago