LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2608. 02951v1 Announce Type: cross Abstract: Preference-based reinforcement learning (PbRL) for general stochastic MDPs often requires training a reward model.
arXiv:2608. 03854v1 Announce Type: new Abstract: When decoder language models are used as classifiers, predicted class probabilities depend on implementation choices, including the prompt template, verbalizer (label-to-token mapping), and scoring rule, that are rarely treated as experimental variables.
arXiv:2507. 14171v3 Announce Type: replace-cross Abstract: Importance-based structured pruning overwhelmingly relies on filter magnitude.
arXiv:2603. 09234v2 Announce Type: cross Abstract: Achieving high perceptual quality without hallucination remains a challenge in generative speech enhancement (SE).
arXiv:2608. 03660v1 Announce Type: new Abstract: Reinforcement fine-tuning (RFT) is widely believed to inherently resist catastrophic forgetting in continual post-training of multimodal large language models.
arXiv:2608. 03606v1 Announce Type: new Abstract: Clinical development is sequential decision-making under uncertainty, where a sponsor must plan a portfolio of experiments from heterogeneous evidence.
arXiv:2605. 20244v2 Announce Type: replace-cross Abstract: We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs.
arXiv:2608. 02646v1 Announce Type: cross Abstract: Decoders of anesthetic state from cortical activity fail across drug classes, most notoriously ketamine, but reported accuracy cannot say whether the neural representation or only the decision threshold has failed; we separate the two in a controlled preparation with ground-truth labels.
arXiv:2608. 02786v1 Announce Type: new Abstract: AI systems can fail silently.
arXiv:2608. 03875v1 Announce Type: cross Abstract: Designing effective reward functions remains a major bottleneck in Reinforcement Learning (RL).
arXiv:2608. 02695v1 Announce Type: cross Abstract: Software supply-chain attacks increasingly exploit an identity gap where compromised maintainer accounts authorize malicious changes.
arXiv:2608. 02150v2 Announce Type: replace-cross Abstract: Embodied intelligence and world models require video understanding systems to go beyond recognizing objects and actions and develop an understanding of physical regularities.
arXiv:2510. 05159v5 Announce Type: replace-cross Abstract: While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain.
arXiv:2608. 03579v1 Announce Type: cross Abstract: Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters.
arXiv:2608. 02820v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace is informative about its actions.
arXiv:2608. 02844v1 Announce Type: cross Abstract: We develop a class of diffusion-based stochastic particle optimisation methods for loss functions with intractable gradients.
arXiv:2608. 03079v1 Announce Type: cross Abstract: Breast core needle biopsy (CNB) is central to breast cancer diagnosis yet remains challenging because limited tissue sampling, lesion heterogeneity, and subtle morphologic overlap can obscure subtype distinctions.
arXiv:2608. 02876v1 Announce Type: new Abstract: Tool-using agents do not merely consume observations: their actions determine what arrives next.
arXiv:2505. 23397v3 Announce Type: replace Abstract: This article presents a structured framework for Human-AI collaboration in Security Operations Centers (SOCs), integrating AI autonomy, trust calibration, and Human-in-the-loop decision making.
arXiv:2608. 03292v1 Announce Type: new Abstract: Long Document Visual Question Answering (LongDocVQA) requires Multimodal Large Language Models (MLLMs) to locate, integrate, and reason over heterogeneous document elements distributed across multiple pages.