OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
Paper • 2506.12618 • Published •
1
Kiran N PRO
Fourwheels2512
AI & ML interests
None yet
Recent Activity
published a Space 1 day ago
Fourwheels2512/live-continual-learning updated a Space 1 day ago
Fourwheels2512/live-continual-learning posted an update 1 day ago
Meets every benchmark. Frontier in Machine Learning.
Live continual learning. @modelbrew.ai
coming soon to www.modelbrew.ai
✨Core highlight features✨
⭐ Zero Forgetting
⭐ Zero cross fact Hallucination
⭐ 3 different models at Qwen 4B, Llama 8B, Phi 14B.
⭐ No LoRA,
⭐ No Router.
⭐ No retraining,
⭐ No made-up answers.
⭐Tamper evidence ledger.
⭐proof of erasing.
⭐Instant update with one forward pass.
⭐Says 'I don't Know' if it doesn't know instead of confident wrong answer.
⭐Governed Memory
⭐Live Learning
⭐Remembers Everything
⭐Keep adding new pages/facts/datasets with our losing old onesOrganizations
commented 5
papers 6 days ago
GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models
Paper • 2506.10946 • Published •
1
Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
Paper • 2601.18699 • Published • 1 •
1
Learning-Time Encoding Shapes Unlearning in LLMs
Paper • 2506.15076 • Published •
1
CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation
Paper • 2408.14572 • Published • 8 •
4
The Next Evolution of AI: From Passive Models to Autonomous Systems
🚀🔥 2
43
#15 opened 3 months ago
by 
oncody
CRMA: Stable Fine-Tuning + Continual Learning for Small LLMs
#2 opened 4 months ago
by Fourwheels2512
Built a stability adapter on top of TRL's SFTTrainer (CRMA + ZClip) — sharing ablation results
#1 opened 4 months ago
by Fourwheels2512
Welcome to CRMA Fine-Tuner — what it does and how to use it
#1 opened 4 months ago
by Fourwheels2512