LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2602. 01179v2 Announce Type: replace Abstract: Gradual domain adaptation (GDA) aims to mitigate domain shift by progressively adapting models from the source domain to the target domain via intermediate domains.
Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities. Many unlearning objectives focus on suppressing undesired answers, while recent target-guided variants specify replacement behavior but still leave update locality largely unconstrained.
Meta AI has recently released the Segment Anything Model (SAM), which demonstrates exceptional zero-shot image segmentation performance across various tasks with remarkable accuracy. Despite its inability to provide accurate segmentation across multiple research fields, SAM still serves as a valuable starting point for supporting the segmentation pipeline process, particularly for tasks that require extensive and senior skills annotations.
We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch gradients suppress rare but useful update directions, causing short-term forgetting at every step. When such knowledge is never revisited, these losses compound into long-term forgetting-the classical failure mode of continual learning.
arXiv:2606. 08938v1 Announce Type: cross Abstract: Clinical diagnosis requires flexible use of multiple reasoning paradigms under incomplete patient information.
arXiv:2606. 07567v1 Announce Type: cross Abstract: Protein function is largely determined by molecular surface geometry and physicochemical complementarity, yet most protein design methods condition only on backbone structure.
arXiv:2605. 03229v2 Announce Type: replace-cross Abstract: Adapting a pretrained language model to a new task often hurts the general capabilities it already had, a problem known as catastrophic forgetting.
arXiv:2606. 07684v1 Announce Type: cross Abstract: Disaggregated serving alleviates memory bottlenecks in Large Language Model (LLM) inference but creates a severe communication bottleneck: transmitting high-dimensional Key-Value (KV) caches often dominates time-to-first-token (TTFT).
arXiv:2510. 27544v2 Announce Type: replace Abstract: Temporal reasoning involves understanding how systems evolve over time through input-driven state transitions.
arXiv:2606. 07970v1 Announce Type: cross Abstract: Current open-weight large language models (LLMs) are prone to malicious finetuning attacks, which could compromise the safety alignment of LLMs with only a few steps of supervised finetuning (SFT) on poisoned datasets.
arXiv:2606. 07676v1 Announce Type: cross Abstract: Spatial transcriptomics (ST) is a powerful tool for exploring biological properties dependent on structure, proximity, and interaction in tissue.
arXiv:2606. 08403v1 Announce Type: cross Abstract: Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views.
arXiv:2606. 09525v1 Announce Type: cross Abstract: During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query.
arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).
arXiv:2606. 09658v1 Announce Type: cross Abstract: Muon has recently emerged as a state-of-the-art optimizer for pretraining Large Language Models (LLMs) and vision classifiers.
arXiv:2606. 08653v1 Announce Type: cross Abstract: Action-supervised fine-tuning of vision-language-action (VLA) policies fits demonstrations effectively but constrains only the directions that change predicted actions, leaving visual structure consistent across action-equivalent states free to collapse.
arXiv:2606. 08669v1 Announce Type: cross Abstract: Voice biometric systems face growing threats from spoofing attacks, yet the evaluation of detection models remains inconsistent across datasets.
arXiv:2606. 08571v1 Announce Type: cross Abstract: Large language models frequently fail in a characteristic way: rather than acknowledging ignorance, they produce fluent but incorrect answers to questions that lie beyond their knowledge boundaries.
arXiv:2208. 00859v2 Announce Type: replace Abstract: We propose a novel method enabling autocompletion of chemical flowsheets.
arXiv:2603. 12666v2 Announce Type: replace-cross Abstract: Retrosynthesis prediction aims to identify reactants that can synthesize a given product molecule.