LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2607. 09073v1 Announce Type: new Abstract: Bayesian optimization routinely warm-starts a target experiment with data from related source tasks, and the multi-task Gaussian process is the textbook surrogate for the job.
arXiv:2604. 01206v2 Announce Type: replace-cross Abstract: We present RELISH (REgression with a Latent Iterative State Head), a novel, lightweight architecture designed for text regression with large language models.
arXiv:2607. 08794v1 Announce Type: cross Abstract: Sand boils on earthen levees are safety-critical defects, but pixel-level detection is limited by scarce annotations.
arXiv:2604. 20140v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks.
arXiv:2607. 08780v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models activate only a sparse subset of experts per token, yet consecutive tokens frequently activate different experts -- causing constant weight swapping between slow storage and fast memory on edge devices.
arXiv:2511. 00651v2 Announce Type: replace Abstract: Telecom networks are rapidly growing in scale and complexity, making effective management, operation, and optimization increasingly challenging.
arXiv:2607. 08974v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) inherit semantic capabilities from pretrained VLMs, yet large-scale post-training on robot data and architectural modifications can reshape the backbone so extensively that it becomes difficult to isolate what the VLM contributes to control.
arXiv:2607. 09316v1 Announce Type: cross Abstract: Thematic indexing -- the practice of assigning structured conceptual labels to sections of text -- is essential to scholarly access in large-scale literary and historical editions, yet it remains a largely manual, labour-intensive process.
arXiv:2607. 09349v1 Announce Type: cross Abstract: Retrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents.
arXiv:2607. 09287v1 Announce Type: new Abstract: Large language models (LLMs) remain expensive to fine-tune because full-parameter updates require substantial memory, compute, and per-task storage.
arXiv:2607. 08877v1 Announce Type: cross Abstract: Pretrained generative robot policies based on flow matching and diffusion have achieved impressive results across a wide range of manipulation tasks.
arXiv:2601. 22313v2 Announce Type: replace Abstract: Large Language Models (LLMs) are rarely static and are frequently updated in practice.
arXiv:2511. 17813v3 Announce Type: replace-cross Abstract: LLM-based simulations can enable controlled studies of civic deliberation, but current systems lack speaker-attributed data and methods for evaluating long-form institutional behavior.
arXiv:2607. 09492v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance.
Vision-language models (VLMs) such as CLIP enable zero-shot classification by comparing image features with text prompts in a shared embedding space. A fundamental property underlying this capability is the global comparability of logits across arbitrary candidate classes.
Two techniques, two different problems, and why the question is not really "which one wins" The post RAG vs Fine-Tuning Explained: What They Actually Do and When to Use Each appeared first on Towards Data Science .
Synthetic data is widely used to train large language models because it is inexpensive to generate and easy to control. As models are increasingly deployed as agents, synthetic trajectories are likely to become an important source of training data for agentic behavior.
arXiv:2607. 08763v1 Announce Type: cross Abstract: Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences.
arXiv:2607. 08014v1 Announce Type: cross Abstract: Federated learning (FL) is a collaborative learning scheme to train deep learning models, where collaborating parties can consolidate their models without sharing local data with other parties, hence preserving data privacy.
arXiv:2607. 07748v1 Announce Type: new Abstract: Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPLs) such as Julia.