Baptiste Colin

bcolin's activity

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

liked 3 datasets 4 days ago

tom-gibbs/multi-turn_jailbreak_attack_datasets

Preview • Updated Sep 7, 2024 • 1.08k • 26

pbevan11/aya_redteaming_consitutional

Viewer • Updated Sep 29, 2024 • 7.42k • 11 • 9

DREAM-17k/DREAM-Red-Teaming-Prompts

Viewer • Updated Dec 11, 2025 • 17.4k • 69 • 10

upvoted a paper 4 days ago

LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation

Paper • 2610.19975 • Published 10 days ago • 82

upvoted a paper 17 days ago

EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling

Paper • 2610.02298 • Published 23 days ago • 60

upvoted a paper 20 days ago

Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures

Paper • 2609.29429 • Published 30 days ago • 29

liked 2 models 22 days ago

nvidia/NemoGuard-JailbreakDetect

Updated Apr 2 • 434 • 42

Sanraj/Qwen3-1.7B-jailbreak-finetuned

2B • Updated Dec 17, 2025 • 120 • 18

upvoted a paper 22 days ago

Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning

Paper • 2609.33781 • Published 27 days ago • 46

upvoted a paper 24 days ago

InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data

Paper • 2609.31394 • Published 29 days ago • 32

liked a model 25 days ago

rogue-security/prompt-injection-jailbreak-sentinel-v2

Text Classification • 0.6B • Updated Mar 11 • 16.5k • 57

upvoted a paper 25 days ago

InternW0: A Foundational Physical World Model for Efficient Real-World Interactions

Paper • 2609.27656 • Published about 1 month ago • 16