Fine-tuning and adaptation

LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.

3,360 stories · RSS feed

Hugging Face Trending Papers
Aug 12

Language-Conditional Dequantization: Recovering What Quantization Steals from Non-English Languages

Aggressive quantization disproportionately harms multilingual capability: in the sub-4B INT3 GPTQ regime, we measure 2-4x larger perplexity degradation on non-English languages than on English. We propose Language-Conditional Dequantization (LCD), a post-hoc method that attaches per-language rank-2 LoRA corrections to the linear layers of an already-quantized model, adding 0.

Hugging Face Trending Papers
Aug 12

JieZi: A Large-Scale Expert-Audited Dataset and Benchmark for Ancient Chinese Character Exegesis

The scholarly exegesis of ancient Chinese characters demands integrating visual observation, linguistic analysis, and historical context. However, existing computational approaches focus narrowly on subtasks such as character recognition and retrieval, lacking the structured datasets and benchmarks required for comprehensive scholarly analysis.

arXiv AI
Aug 12

MIRA: Medical Image Reflection for Agentic Diagnosis

arXiv:2608. 10827v1 Announce Type: cross Abstract: Medical visual agents can use tools to inspect images and retrieve external knowledge, but indiscriminate tool use may introduce noisy or misleading evidence.

By Shengzhi Wang, Jun Yang, Kai Wu, Xiaozhong Ji, Yiwen Ye, Ziyang Chen, Mingliang Xiong, Wen Fang, Mingqing Liu, Mengyuan Xu, Miaoxuan Shan, Caiyan Liu, Bin He, Qingwen Liu
arXiv Machine Learning
Aug 12

Retrieval-Augmented Vision Foundation Models for Robust Leukemia Cell Classification across Multiple Microscopy Datasets

arXiv:2608. 10657v1 Announce Type: cross Abstract: Leukemia cell image classification is challenged by real-world domain shifts from acquisition, staining, illumination, and site protocols, causing single-dataset models to generalize poorly in real clinical scenarios.

By Carlos Zamora, Hiram Zuniga, Ulises Orozco-Rosas, Kenia Picos
arXiv AI
Aug 12

MarkNull: Model-Agnostic Watermark Removal in AI-Generated Images via On-Manifold Latent Manipulation

arXiv:2608. 10166v1 Announce Type: cross Abstract: Digital watermarking has emerged as a critical technique for provenance and copyright attribution in AI-generated imagery, yet its robustness against realistic, model-agnostic removal attacks remains poorly explored.

By Jie Cao, Qi Li, Zelin Zhang, Xiaodong Wu, Lingshuang Liu, Xiangman Li, Jianbing Ni
arXiv Machine Learning
Aug 12

MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale

arXiv:2608. 10333v1 Announce Type: new Abstract: LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or tool-argument construction.

By Yuhang Yao, Zeyu Wang, Wanyi Chen, Tongyun Yang, Yuhang Han, Jie Xiao, Chengke Bao, Tianyi Zhao, Lynn Ai, Eric Yang, Tianyu Shi
arXiv Machine Learning
Aug 12

Link-adaptive digital twin for robust physical-layer modeling in hybrid-amplified ultra-wideband optical networks

arXiv:2608. 10517v1 Announce Type: cross Abstract: Accurate physical-layer modeling is increasingly essential for reliable ultra-wideband operation and capacity optimization, especially under the intensified inter-channel stimulated Raman scattering (ISRS) effect.

By Xiaoxuan Gao, Rentao Gu, Yingchun Wang, Xinyi Liu, Junshi Gao, Yuefeng Ji
arXiv AI
Aug 12

MazzikaAI: A knowledge-based performance-to-prompt compiler for real-time Arabic maqam accompaniment with a streaming text-to-music model

arXiv:2608. 10360v1 Announce Type: cross Abstract: Arabic maqam music microtonal, modal, and built on ornamented call and response is among the traditions most underserved by generative music models, whose training frameworks remain predominantly Western and equaltempered.

By Jiaxin Du, Boulbaba Abdeljaouad, Yong Zhuang, Haoyu Li
arXiv Machine Learning
Aug 12

UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations

arXiv:2608. 10835v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input.

By Dvir Samuel, Guy Bar-Shalom, Fabrizio Frasca, Ethan Fetaya, Yftah Ziser, Gal Chechik, Haggai Maron