The study investigates how the rank of Low‑Rank Adaptation (LoRA) affects diffusion model fine‑tuning on CIFAR‑10 using a DDPM U‑Net. Experiments with ranks 2, 4, 8, 16, and 32 show that moderate ranks—particularly rank 4—yield the best FID scores while keeping trainable parameters, runtime, and GPU memory low. Higher ranks offer only marginal improvements at a higher computational cost, suggesting that small‑to‑moderate ranks are efficient defaults for fixed training budgets.
arXiv:2606. 12921v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) significantly reduces compute and memory costs for finetuning Deep Learning models but is often harder to tune than dense training: when using factor-wise optimizers such as AdamW, it is sensitive to initialization choices, its optimal learning rates transfer poorly across ranks, and it often fails to beat dense baselines.
arXiv:2607. 05711v1 Announce Type: new Abstract: Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications.
The paper introduces ISO-LoRA, an optimizer that improves rank utilization in Low‑Rank Adaptation (LoRA) by coupling factor updates through spectral descent on the induced tangent perturbation in weight space. Experiments on GPT‑2 adaptation show that standard optimizers like AdamW concentrate updates in a few singular directions, whereas ISO-LoRA distributes energy more evenly, leading to higher effective rank and better downstream performance across 0.1B‑7B models. The authors provide theoretical guarantees under a stylized spiked‑gradient model and demonstrate that ISO-LoRA consistently outperforms factor‑wise optimizers, especially at moderate‑to‑large LoRA ranks.
arXiv:2608.20818v1 Announce Type: cross Abstract: The matrix-aware optimizer Muon improves large model training by balancing updates across singular directions, yet its scaling behavior and end-to-en...
arXiv:2607. 24665v1 Announce Type: cross Abstract: Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capacity grows.
The paper introduces BYOD (Build Your Own DLM), a LoRA‑only method that converts autoregressive language models into diffusion language models without changing the base architecture. BYOD successfully converts Gemma 2 9B, Llama 3.1 8B, Qwen2.5 7B, and Ministral 8B, adding adapters that occupy only 4.1‑5.8% of the total parameters while keeping all base‑model weights frozen. The conversions require at most 102.4 M tokens and a few hours on a single GPU, and the resulting diffusion models can generate from fully masked sequences, use bidirectional context, and retain much of the original model’s knowledge, with the Gemma conversion achieving the highest accuracy on a nine‑task benchmark.
arXiv:2606. 24119v1 Announce Type: new Abstract: Discrete diffusion language model (DLM) fine-tuning inherits inexpensive diagnostics from denoising-time confidence monitors, but their PEFT-training meaning is untested.
arXiv:2609.06072v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) of mixture-of-experts (MoE) models commonly attaches a separate low-rank adapter to each expert. This expert-w...
arXiv:2608. 19800v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) is a prominent fine-tuning method for large models, achieving competitive performance with reduced memory overhead.
arXiv:2610.32243v1 Announce Type: new Abstract: Post-training quantization (PTQ) to FP4 has emerged as a key technique for reducing large language model inference cost, especially on Blackwell GPUs,...
arXiv:2607. 01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation.