LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2607. 28670v3 Announce Type: replace Abstract: A stochastic Gumbel-Top-K router defines, for every token of a mixture-of-experts (MoE) model, a routing law: a distribution over ordered expert lists and mixture weights.
arXiv:2608. 15917v1 Announce Type: cross Abstract: Large-scale pre-training has made robot policy fine-tuning increasingly data-efficient, but this progress has largely been driven by datasets and embodiments built around simple parallel-jaw grippers.
arXiv:2608. 16429v1 Announce Type: new Abstract: Foundational models for tabular data have made significant progress in recent years, with TabICLv2 reporting state-of-the-art performance on several tabular classification tasks.
arXiv:2608. 16502v1 Announce Type: new Abstract: Large-scale agents increasingly rely on retrieval to access external capabilities.
arXiv:2604. 10496v2 Announce Type: replace Abstract: Outliers have emerged as a fundamental bottleneck in preserving accuracy for low-precision large models, particularly within Mixture-of-Experts (MoE) architectures that are increasingly central to large-scale language modeling.
arXiv:2608. 15843v1 Announce Type: cross Abstract: Characterising electrophysiological properties of cardiac tissue efficiently and accurately from spatially sparse intracardiac measurements is clinically important for localising ablation targets and improving arrhythmia treatment.
arXiv:2608. 15579v1 Announce Type: cross Abstract: Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long horizons, tool-use discipline, context persistence, heterogeneous clusters, and evaluation reuse.
arXiv:2603. 24575v2 Announce Type: replace-cross Abstract: Scalable Vector Graphics (SVG) are essential for technical illustration and digital design, offering resolution independence and semantic editability.
arXiv:2501. 12147v2 Announce Type: replace-cross Abstract: Selecting appropriate training data is crucial for instruction fine-tuning of large language models (LLMs), which aims to (1) elicit strong capabilities, and (2) achieve balanced performance across different tasks.
arXiv:2608. 15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads.
arXiv:2608. 16480v1 Announce Type: cross Abstract: We present RISE (Roadside Infrastructure Sequence Understanding and Evaluation), a framework spanning metric 3D tracking and structured vision-language reasoning in roadside sequences.
arXiv:2608. 16622v1 Announce Type: cross Abstract: Multimodal harmful meme detection is typically formulated as image--text harmfulness classification.
arXiv:2506. 07449v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have driven their adoption in recommender systems through Retrieval-Augmented Generation (RAG) frameworks.
arXiv:2608. 16661v1 Announce Type: cross Abstract: Hyperspectral reflectance spectroscopy enables non-destructive estimation of plant functional traits, yet current deep learning approaches process spectra as one-dimensional sequences, which limits how they capture long-range inter-band dependencies.
arXiv:2511. 11439v3 Announce Type: replace-cross Abstract: Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics.
arXiv:2608. 11980v2 Announce Type: replace-cross Abstract: Semantic-ID generative recommenders represent each item as a short sequence of discrete semantic tokens and predict the next item by autoregressively generating this token sequence.
arXiv:2608. 15976v1 Announce Type: new Abstract: A learning system can occupy execution states that are indistinguishable under every declared present-behavior readout yet respond differently to future training.
arXiv:2608. 15690v1 Announce Type: cross Abstract: Text-to-audio-video (T2AV) generation models produce a video and its soundtrack from a textual description, but offer no control over whose voice speaks in the output.
arXiv:2608. 15381v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of large language models, but its factorized parameterization creates a tension between accurate aggregation of local updates and continuity of locally optimized factors.
arXiv:2608. 15900v1 Announce Type: cross Abstract: Data-driven materials discovery interpolates more reliably than it extrapolates and seldom reaches new structure types.