LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2609.13486v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning decoder-only large language models (LLMs) for retrieval yields strong first-stage retrievers, with effectivene...
arXiv:2404.00727v3 Announce Type: replace Abstract: All state-of-the-art coreference resolution (CR) models involve finetuning a pretrained language model. Whether the superior performance of one CR...
arXiv:2609.13226v1 Announce Type: new Abstract: Machine learning for neglected tropical diseases is limited by data, not algorithms: public annotated image sets for leprosy (Hansen's disease) number...
arXiv:2609.13854v1 Announce Type: new Abstract: Facial emotion recognition (FER) in real-world environments remains challenging due to unconstrained imaging conditions, including multiple faces, occl...
arXiv:2609.14106v1 Announce Type: new Abstract: We evaluated parameter-efficient fine-tuning (PEFT) of the Segment Anything Model (SAM) for liver tumor segmentation in abdominal CT of colorectal live...
arXiv:2609.14350v1 Announce Type: new Abstract: Medical vision-language models (VLMs) allow a single model to perform clinical image analysis tasks ranging from diagnosis classification to report gen...
arXiv:2609.13504v1 Announce Type: new Abstract: Recent developments in feed-forward 3D reconstruction resulted in models which can recover dense scene representations and camera motion solely from an...
The paper introduces an enhanced end‑to‑end circuit analysis framework built on Gemini 2.5 Pro, targeting engineering education. It addresses two key failure modes—circuit‑recognition hallucinations and reasoning‑process hallucinations—by adding a YOLO detector for source polarity re‑identification and an ngspice verification loop for iterative refinement. The resulting pipeline achieves 97.59 % accuracy on 83 undergraduate problems, markedly outperforming the baseline Gemini model and demonstrating significant gains across varied diagram styles and textbooks.
Q‑SiT is a unified framework that trains large multimodal models to perform both image quality scoring and interpreting simultaneously. By converting standard IQA datasets into question‑answer pairs and adding human‑annotated interpreting data, the model learns to quantify overall quality and describe perceived attributes. An efficient balance strategy optimizes data mix ratios on lightweight models before scaling to full‑size LMMs, reducing computational cost while improving cross‑task knowledge transfer.
arXiv:2609.14570v1 Announce Type: cross Abstract: Multi-agent LLM systems combine multiple inference calls, but prior work often confounds how calls are connected with how they are diversified. We st...
arXiv:2609.14998v1 Announce Type: new Abstract: Recent work shows that models that learn to reward hack on RL environments can become broadly misaligned, and that reframing reward hacking as acceptab...
arXiv:2609.15344v1 Announce Type: new Abstract: We study the adaptation of pretrained language models to univariate time-series forecasting through a parameter-efficient transfer learning framework,...
arXiv:2609.13259v1 Announce Type: cross Abstract: Virtual Try-On (VTON) aims to dress a person with the reference garment, producing visually reasonable results aligned with human preferences. Turnin...
arXiv:2609.13264v1 Announce Type: cross Abstract: Generating human-centric videos that preserve both visual identity and person-specific expressive behavior remains a fundamental challenge. In additi...
arXiv:2609.13287v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) achieve high decoding efficiency through block-parallel, arbitrary-order generation, making them attractive f...
arXiv:2609.15606v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress on short video understanding yet remain limited on long videos due to the...
arXiv:2603.13359v2 Announce Type: replace Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusa...
arXiv:2609.12606v2 Announce Type: replace Abstract: While multimodal reasoning has advanced rapidly, solving complex geometry problems critically hinges on active visual assistance, such as construct...
arXiv:2609.13507v1 Announce Type: new Abstract: Brain-computer interfaces (BCIs) decode neural activity to restore lost function. Typically, training a high-performance neural decoder requires a larg...
arXiv:2609.13615v1 Announce Type: new Abstract: For our submission to the WMT26 Creole Language Translation Shared Task, we focus on machine translation (MT) models for Pacific creoles: Tok Pisin, Bi...