LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2607. 21332v1 Announce Type: cross Abstract: Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties.
arXiv:2607. 20666v1 Announce Type: cross Abstract: The robustness of machine learning techniques across heterogeneous network domains remains an open challenge in optical networks.
arXiv:2607. 20952v1 Announce Type: new Abstract: Latent, or silent, reasoning lets language models carry out intermediate computation in continuous vector space instead of words, and is widely assumed to function as an internal scratchpad the model actively consults during inference.
arXiv:2607. 20914v1 Announce Type: new Abstract: Federated parameter-efficient fine-tuning (PEFT) enables communication-efficient adaptation of large pretrained models on decentralized edge data, but it remains fragile under non-IID client heterogeneity.
arXiv:2607. 03819v3 Announce Type: replace-cross Abstract: Challenges remain in ego-centric 3D scene generation due to limited view overlap and the dominant influence of individual perspectives on scene interpretation.
arXiv:2607. 20778v1 Announce Type: new Abstract: Weather forecasting foundation models (FMs) are increasingly fine-tuned to predict air quality, offering fast global pollution forecasts at lower computational cost than conventional chemical transport models.
arXiv:2607. 20481v1 Announce Type: new Abstract: Local-cloud collaboration is a practical way to deploy large language models under resource constraints, but existing methods often rely on trained routers or collaboration-aware finetuning that tie routing behavior to a particular operating regime.
arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.
arXiv:2607. 20487v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to answer questions about political information, including in election-adjacent information settings where factual errors and ideological distortions are high-stakes.
arXiv:2607. 20433v1 Announce Type: cross Abstract: While language models remain frozen at their training state, the world evolves continuously.
arXiv:2602. 12304v5 Announce Type: replace-cross Abstract: Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual prompts.
arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.
arXiv:2607. 21366v1 Announce Type: cross Abstract: Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge.
arXiv:2607. 20472v1 Announce Type: new Abstract: When a user asks a language model something harmful, is it a genuine attack or a misunderstood but well-meaning question?
arXiv:2607. 21090v1 Announce Type: cross Abstract: We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explanations - the extent to which a model's generated reasoning accurately reflects its internal decision-making process.
arXiv:2607. 21522v1 Announce Type: cross Abstract: Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challenging.
arXiv:2607. 21498v1 Announce Type: cross Abstract: A rhetorical figure that Cicero and Quintilian catalogued two thousand years ago reappears, systematically, in the text of large language models: epanorthosis, the self-correction of the specimen {\guillemotleft}This is not a course.
arXiv:2607. 20913v1 Announce Type: new Abstract: Fine-tuning large diffusion models for new domains or styles involves a trade-off: improving target-specific generation often degrades the pretrained model's broad generative capability.
arXiv:2607. 20470v1 Announce Type: new Abstract: Enhancing the task-specific capabilities of Large Language Models (LLMs) primarily requires substantial instruction-tuning datasets.
arXiv:2607. 20438v1 Announce Type: cross Abstract: Preference-based post-training is usually understood through endpoint behavior, yet the learned update that produces this behavior remains largely opaque.