⚙️ LLM Fine-tuning - inarcissuss · Scour

🧠LLM Engineering arXiv·

Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning

🔀LoRA imranahamed.substack.com·

Tracing a silent-corruption bug in differentially private LoRA fine-tuning

Covers LoRA: Low-Rank Adaptation of Large Language Models

Discussed on Substack

🧠LLM arXiv·

Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents

🗣️Large Language Models arXiv·

Can LLMs Reliably Self-Report Adversarial Prefills, and How?

✨Generative AI arXiv·

MythraGen: Two-Stage Retrieval Augmented Art Generation Framework

🗣️Large Language Models arXiv·

Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations

🗣️Large Language Models arXiv·

Latent Personal Memory: Represent personal memory as dynamic soft prompts

🧠LLM Engineering fig.inc·

Fixing Failures in Browser-Use Models: Why More Data Isn't Enough

Covers 3 stories including Overview - Agent Skills

Discussed on Hacker News

🧠LLM Training arXiv·

ConnectomeBench2: A Unified Benchmark for Automated Connectomic Proofreading

🎯Post-training arXiv·

Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs

Log in to enable infinite scrolling