Guilherme Monteiro

guicybercode's activity

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

New activity in Horizon-Labs/prompt-injection-guard-base 2 days ago

Per-language false alarms and the int8 ONNX file on long inputs

5

#1 opened 18 days ago by

guicybercode

New activity in apollowmm/ragsec-prompt-injection 2 days ago

Ungrounded answers without an attacker: retrieval or model?

❤️ 1

2

#1 opened 5 days ago by

guicybercode

commented a paper 5 days ago

Think Less, Locally: Local Preference Learning for Reasoning Compression

Paper • 2611.04814 • Published 6 days ago • 64 •

10

New activity in RelyD/prompt-injection-detector 5 days ago

Multilingual-cased on Portuguese prompts?

2

#1 opened 6 days ago by

guicybercode

New activity in Horizon-Labs/prompt-injection-eval-suite 5 days ago

Native or translated rows in the synthetic multilingual configs

2

#2 opened 18 days ago by

guicybercode

commented 2 papers 5 days ago

You don't need long context

Paper • 2611.05306 • Published 6 days ago • 22 •

6

Think Less, Locally: Local Preference Learning for Reasoning Compression

Paper • 2611.04814 • Published 6 days ago • 64 •

10

commented a paper 6 days ago

Follow the Gradient: Tracing Safety Degradation Back to Training Data

Paper • 2610.37481 • Published 13 days ago • 32 •

3

New activity in Tobiashopf/ptbr-finance-eval 6 days ago

Casos de injeção indireta?

#2 opened 6 days ago by

guicybercode

New activity in Brosh123/qwen3.5-9b-q2-gguf 6 days ago

Source quantization for the Q2_K?

#1 opened 6 days ago by

guicybercode

New activity in Tutanka01/Qwen3.5-0.8B-loopfix-GGUF 6 days ago

Does the edit hold outside French, and on Q4_K_M?

#1 opened 6 days ago by

guicybercode

commented a paper 6 days ago

Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them

Paper • 2609.05881 • Published 15 days ago • 8 •

7

New activity in DevTheusP/qwen2.5-0.5b-fact-extractor-ptbr 7 days ago

Why does the student beat the teacher on v2_keyed retrieval?

4

#1 opened 7 days ago by

guicybercode

New activity in mASMK2/agent-verdict-bench-ptbr 7 days ago

The falso_verde left in arm B

#1 opened 7 days ago by

guicybercode

New activity in Genrius-AI/2bit-gguf-wikitext2-eval 7 days ago

Perplexity windows versus a task check for the 2-bit Qwen3.5-2B files

#1 opened 7 days ago by

guicybercode

commented a paper 7 days ago

Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them

Paper • 2609.05881 • Published 15 days ago • 8 •

7

commented 2 papers 9 days ago

Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data

Paper • 2610.37386 • Published 13 days ago • 26 •

6

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

Paper • 2610.31309 • Published 18 days ago • 13 •

7

commented 2 papers 11 days ago

Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems

Paper • 2610.30418 • Published 19 days ago • 21 •

11

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 16 days ago • 4 •

13