LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2607. 20057v1 Announce Type: cross Abstract: Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules.
arXiv:2607. 19354v1 Announce Type: new Abstract: Spreadsheet applications are used by hundreds of millions worldwide, yet writing formulas remains a significant barrier.
arXiv:2504. 03707v2 Announce Type: replace-cross Abstract: Emotion recognition is crucial for advancing mental health, healthcare, and technologies such as brain-computer interfaces.
arXiv:2607. 20145v1 Announce Type: cross Abstract: Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlapped communication overhead, and inefficient kernel execution.
arXiv:2607. 19956v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined.
arXiv:2607. 20385v1 Announce Type: cross Abstract: Optical Character Recognition (OCR) for Persian remains substantially less mature than for Latin-script languages despite Persian being spoken by more than 110 million people across multiple countries.
arXiv:2607. 19421v1 Announce Type: cross Abstract: Silicon-photonic (SiPh) accelerators have emerged as a promising platform for Vision Transformer (ViT) inference by performing matrix multiplications on microring-resonator (MRR) banks with high throughput and energy efficiency.
arXiv:2607. 20339v1 Announce Type: new Abstract: Constitutive modeling under uncertainty remains a central challenge for reliable mechanics simulations, particularly when the available stress-deformation data are sparse, noisy, or heterogeneous.
arXiv:2607. 20367v1 Announce Type: new Abstract: Correlation alignment and the maximum mean discrepancy are two widely used distribution-matching frameworks for unsupervised domain adaptation (UDA).
arXiv:2607. 20194v1 Announce Type: new Abstract: The development of organic light-emitting diode (OLED) materials faces the compounded challenges of an astronomically large chemical space, stringent quantum-chemical constraints, and a scarcity of labeled data.
arXiv:2512. 16300v3 Announce Type: replace Abstract: Existing image forgery detection (IFD) methods either exploit low-level, semantics-agnostic artifacts or rely on multimodal large language models (MLLMs) with high-level semantic knowledge.
arXiv:2607. 19395v1 Announce Type: cross Abstract: Small language models are attractive backbones for interactive agents, but direct distillation from strong teacher trajectories often turns rich multi-turn behavior into one-shot imitation targets.
arXiv:2607. 19864v1 Announce Type: cross Abstract: Diabetic retinopathy is a leading cause of preventable blindness; its early lesions are small, low contrast, and easily missed in manual screening.
arXiv:2607. 19674v1 Announce Type: cross Abstract: Federated Graph Neural Networks (FedGNNs) are highly vulnerable to backdoor poisoning, yet existing defenses typically rely on rule-based approaches that lack semantic understanding, making them vulnerable to stealthy triggers and harmful to benign structures.
arXiv:2607. 20056v1 Announce Type: cross Abstract: Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text.
arXiv:2607. 19364v1 Announce Type: new Abstract: Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models, but SAE-based steering methods often rely on learned steering objectives or single-criterion feature selection.
arXiv:2603. 07466v2 Announce Type: replace-cross Abstract: Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs).
arXiv:2606. 20785v2 Announce Type: replace Abstract: Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies.
arXiv:2607. 19391v1 Announce Type: cross Abstract: Low-Rank Adaptation is widely used for parameter-efficient fine-tuning, yet existing methods typically assign the same adapter rank to every transformer layer despite their heterogeneous adaptation requirements.
arXiv:2607. 19371v1 Announce Type: new Abstract: Large language model (LLM)-based Socratic tutors increasingly guide students through multi-turn questioning, but they can suffer from scaffolding collapse: under sustained student pressure, a tutor gradually abandons guided inquiry and reveals solutions directly.