Guilherme Monteiro

guicybercode's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented 3 papers 1 day ago

Beyond Benchmarks: Can Small Open-Weight Models Get Real Coding Work Done?

Paper • 2610.34241 • Published 4 days ago • 12 •

7

Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5

Paper • 2610.33732 • Published 5 days ago • 9 •

8

Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models

Paper • 2610.31198 • Published 7 days ago • 26 •

5

New activity in pbhappliedsystems/quant-eval-agent-arena 1 day ago

What should we compare next?

3

#3 opened 20 days ago by

pbhappliedsystems

commented 3 papers 1 day ago

Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization

Paper • 2610.31309 • Published 7 days ago • 20 •

4

Beyond Benchmarks: Can Small Open-Weight Models Get Real Coding Work Done?

Paper • 2610.34241 • Published 4 days ago • 12 •

7

Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5

Paper • 2610.33732 • Published 5 days ago • 9 •

8

New activity in HelloSun/Qwen3.6-35B-A3B-GGUF_CPU_OPT 1 day ago

Which of the nine changes carry over to AVX2-only CPUs?

#1 opened 1 day ago by

guicybercode

commented a paper 2 days ago

Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems

Paper • 2610.30418 • Published 8 days ago • 27 •

9

New activity in sandovs/parakeet-tdt-0.6b-v3-ptBR-TAGARELA-onnx-q4 2 days ago

WER of P-q4 against the source ONNX export

2

#1 opened 3 days ago by

guicybercode

New activity in jmrenouard/microllm-guardrail-int8 3 days ago

Prompt-injection rubric on Portuguese input

4

#1 opened 6 days ago by

guicybercode

commented 2 papers 3 days ago

Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems

Paper • 2610.30418 • Published 8 days ago • 27 •

9

Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models

Paper • 2610.31198 • Published 7 days ago • 26 •

5

New activity in inples-tech/anonimato-ner-ptbr 3 days ago

int8 versus fp32 recall and the 24 hand-written fragments

#1 opened 3 days ago by

guicybercode

New activity in linc42/pii-ner-pt-br-bertimbau 3 days ago

Model-only numbers on BR-Agentic-PII-Benchmark

#1 opened 3 days ago by

guicybercode

commented 2 papers 4 days ago

SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs

Paper • 2610.31062 • Published 7 days ago • 32 •

8

The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction

Paper • 2609.18063 • Published Sep 16 • 31 •

9

commented 2 papers 5 days ago

Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought

Paper • 2610.30755 • Published 7 days ago • 38 •

8

SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs

Paper • 2610.31062 • Published 7 days ago • 32 •

8

New activity in halilneed/turkish-prompt-injection-false-alarm-benchmark 5 days ago

Task instructions as the hardest benign subset

2

#2 opened 9 days ago by

guicybercode