LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2508. 12116v2 Announce Type: replace-cross Abstract: As numerous instruction-tuning datasets continue to emerge, dynamically balancing and optimizing their mixtures has become a critical challenge.
arXiv:2607. 02576v1 Announce Type: cross Abstract: Parameter-Efficient Fine-Tuning (PEFT) commonly adapts pretrained weights through low-rank updates, and recent methods further exploit the singular value decomposition (SVD) of the base weight for initialization or subspace selection.
arXiv:2508. 04928v5 Announce Type: replace-cross Abstract: We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images.
arXiv:2510. 01460v4 Announce Type: replace-cross Abstract: Offline-to-online reinforcement learning (RL) has emerged as a practical paradigm that leverages offline datasets for pretraining and online interactions for fine-tuning.
arXiv:2508. 10031v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks.
arXiv:2601. 09448v3 Announce Type: replace-cross Abstract: Conventional audio equalization is a static process that requires manual and cumbersome adjustments to adapt to changing listening contexts (e.
arXiv:2607. 04423v1 Announce Type: cross Abstract: Unified Multimodal Models (UMMs) integrate image understanding and generation within a single architecture, yet how the two tasks interact remains understudied.
arXiv:2606. 22574v2 Announce Type: replace-cross Abstract: While synthetic data generation resolves the manual labeling bottleneck in computer vision, minimizing the syn-to-real domain gap requires optimizing rendering variables.
arXiv:2505. 24415v2 Announce Type: replace-cross Abstract: Automated evaluation of movement quality can enhance physiotherapeutic treatment and sports training by providing objective, real-time feedback.
arXiv:2512. 05672v2 Announce Type: replace-cross Abstract: Recent approaches in controllable novel view video generation often rely on fine-tuning pre-trained Video Diffusion Models (VDMs).
arXiv:2607. 03005v1 Announce Type: new Abstract: In high-dimensional Ising model estimation, target sample sizes are often limited, and effectively using auxiliary binary datasets of unknown relevance remains challenging.
arXiv:2607. 03094v1 Announce Type: new Abstract: Electroencephalography (EEG) decoding for brain-computer interfaces (BCIs) faces a major challenge: substantial inter-subject variability limits effective cross-subject generalization.
arXiv:2607. 04919v1 Announce Type: new Abstract: Deploying a time series foundation model requires GPU infrastructure, engineering overhead, and carries no guarantee of improvement over XGBoost.
arXiv:2607. 02995v1 Announce Type: cross Abstract: Vision-language models can exhibit visual concept-conditioned divergence: given images containing demographic features, corporate logos, or ideological symbols, some models produce unusually uniform responses that differ from what peer models say about the same input.
arXiv:2607. 03591v1 Announce Type: cross Abstract: Recent studies on multimodal traffic accident understanding have mainly relied on infrastructure-camera footage, satellite imagery, or structured crash records.
arXiv:2607. 03530v1 Announce Type: new Abstract: We introduce MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal LLMs (MLLMs) with an executable mechanism for "mental" visualization.
arXiv:2510. 08048v4 Announce Type: replace-cross Abstract: Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business conversion.
arXiv:2604. 17184v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can generate plausible code patches, but plausibility is not enough for automated repair: a patch must compile, pass tests, and remove the target vulnerability.
arXiv:2607. 04428v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising a masked sequence, offering a parallel alternative to autoregressive models, but eliciting strong reasoning through post-training remains difficult: supervised fine-tuning is off-policy and suffers from exposure bias, while reinforcement learning gives only sparse, sequence-level rewards and is hard to apply without tractable sequence likelihoods.
arXiv:2607. 04306v1 Announce Type: new Abstract: Distilling a fine-tuned teacher into a LoRA-adapted student is a standard recipe for parameter-efficient compression, but output-level KD does not explicitly control which rank-$r$ weight subspace the adapter occupies.