LLM Digest

Story

arxiv_cs_cl · Nov 12, 2026 · paper

Source brief

Maximizing Capacity Utilization of LoRA Adapters for Mitigating the Learning-Forgetting Trade-off

arxiv.orgNov 12, 2026
original source linked

In brief

Low-Rank Adaptation (LoRA) often underperforms full fine-tuning, especially in heterogeneous and continual-learning settings in which substantial forgetting occurs. In general, it suffers from an undesirable learning-...

Feed lens

eval

Read the original at arxiv.org →Open in live feed Read that day’s brief

Maximizing Capacity Utilization of LoRA Adapters for Mitigating the Learning-Forgetting Trade-off

Earlier in this thread 4 items

Generate per-session LoRA adapters in <1s for agentic inference efficiency

Sckwoky at SHROOM-Visions: Character-Level Hallucination-Span Detection in Image-Conditioned VLMs via Dual-Prompted LoRA Decoders

Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters

CalibraRL: Confidence-Calibrated Reinforcement Learning for Mitigating Hallucinations in RAG