Guilherme Monteiro

guicybercode's activity

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

commented a paper about 22 hours ago

Follow the Gradient: Tracing Safety Degradation Back to Training Data

Paper • 2610.37481 • Published 8 days ago • 30 •

3

New activity in Tobiashopf/ptbr-finance-eval about 22 hours ago

Casos de injeção indireta?

#2 opened about 22 hours ago by

guicybercode

New activity in Brosh123/qwen3.5-9b-q2-gguf about 22 hours ago

Source quantization for the Q2_K?

#1 opened about 22 hours ago by

guicybercode

New activity in Tutanka01/Qwen3.5-0.8B-loopfix-GGUF about 22 hours ago

Does the edit hold outside French, and on Q4_K_M?

#1 opened about 22 hours ago by

guicybercode

New activity in RelyD/prompt-injection-detector about 22 hours ago

Multilingual-cased on Portuguese prompts?

1

#1 opened about 22 hours ago by

guicybercode

commented a paper 1 day ago

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

Paper • 2609.05881 • Published 10 days ago • 7 •

7

New activity in DevTheusP/qwen2.5-0.5b-fact-extractor-ptbr 1 day ago

Why does the student beat the teacher on v2_keyed retrieval?

4

#1 opened 2 days ago by

guicybercode

New activity in mASMK2/agent-verdict-bench-ptbr 2 days ago

The falso_verde left in arm B

#1 opened 2 days ago by

guicybercode

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

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

#1 opened 2 days ago by

guicybercode

commented a paper 2 days ago

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

Paper • 2609.05881 • Published 10 days ago • 7 •

7

commented 2 papers 4 days ago

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

Paper • 2610.37386 • Published 8 days ago • 25 •

6

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

Paper • 2610.31309 • Published 13 days ago • 13 •

7

commented 3 papers 6 days ago

Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems

Paper • 2610.30418 • Published 14 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 11 days ago • 4 •

13

Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance

Paper • 2610.35328 • Published 9 days ago • 6 •

6

New activity in RenatoSpessotto/qwen3.5-2b-aspectos-reviews-ptbr-lora 6 days ago

CPU-only latency and a GGUF build of the adapter

#1 opened 6 days ago by

guicybercode

commented 3 papers 6 days ago

Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance

Paper • 2610.35328 • Published 9 days ago • 6 •

6

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

Paper • 2610.37386 • Published 8 days ago • 25 •

6

ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning

Paper • 2610.34886 • Published 9 days ago • 3 •

3

commented a paper 8 days ago

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

Paper • 2610.34241 • Published 10 days ago • 9 •

7