Fine-tuning and adaptation

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

3,721 stories · RSS feed

Hugging Face Trending Papers
Jul 2

ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA

Recent multimodal large language models (MLLMs) have substantially advanced video understanding, yet long-form video QA remains challenging under fixed input token budgets, where uniform sampling can be inefficient for evidence localization. We propose ReQuest , an uncertainty-driven, question-adaptive keyframe selection pipeline that aligns question intent with relevant video content through selective computation.

arXiv AI
Jul 2

Diffusion-GR2: Diffusion Generative Reasoning Re-ranker

arXiv:2607. 01170v1 Announce Type: cross Abstract: Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering a candidate list, but they are slow at inference: an autoregressive (AR) decoder spends one sequential forward pass per reasoning token, and the reasoning trace far exceeds the ranking it produces.

By Zhuoxuan Zhang (Yang), Kangqi Ni (Yang), Yuhang Chen (Yang), Mingfu Liang (Yang), Xiaohan Wei (Yang), Yunchen Pu (Yang), Fei Tian (Yang), Chonglin Sun (Yang), Frank Shyu (Yang), Adam (Yang), Song, Sandeep Pandey, Luke Simon, Tianlong Chen, Xi Liu
arXiv Machine Learning
Jul 2

Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices

arXiv:2607. 01001v1 Announce Type: cross Abstract: Radiomics is the established approach for CT-based lung cancer phenotyping, yet comparisons with foundation models rarely isolate contributions of feature extractor, classification head, and segmentation choice, or test cross-cohort robustness.

By Nils Neukirch, Martin Maurer, Nils Strodthoff
arXiv Machine Learning
Jul 2

Zeroth-Order Optimization at the Edge of Stability

arXiv:2604. 14669v2 Announce Type: replace Abstract: Zeroth-order (ZO) methods are widely used when gradients are unavailable or prohibitively expensive, including black-box learning and memory-efficient fine-tuning of large models, yet their optimization dynamics in deep learning remain underexplored.

By Minhak Song, Liang Zhang, Bingcong Li, Niao He, Michael Muehlebach, Sewoong Oh
arXiv Machine Learning
Jul 2

ZO-Act: Efficient Zeroth-Order Fine-Tuning via One-Shot Activation-Informed Low-Rank Subspaces

arXiv:2607. 01125v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables fine-tuning large language models when backpropagation is unavailable or memory-prohibitive, but existing methods often perturb full model weights or randomly constructed low-dimensional subspaces, yielding high-variance estimates and limited performance.

By Xun Dong, Yibo Xu, Naigang Wang, Xin Li, Penghang Yin, Zi Yang
arXiv AI
Jul 2

EgoGapBench: Benchmarking Egocentric Action Selection in Multi-Agent Scenes

arXiv:2607. 00547v1 Announce Type: cross Abstract: Existing egocentric benchmarks have primarily constructed the egocentric setting from first-person-view data, which makes it difficult to evaluate egocentric perspective itself in isolation.

By Jihyeok Jung (KAIST AI), Jeewu Lee (Sogang University), Sanghyeop Kim (Sogang University), Chanhee Han (Ministry of Science and ICT), Seong Joon Oh (KAIST AI)
arXiv AI
Jul 2

Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use

arXiv:2607. 01084v1 Announce Type: new Abstract: While Large Language Model (LLM) agents demonstrate proficiency in static benchmarks, their deployment in real-world scenarios is hindered by the dynamic nature of user queries, tool sets, and interaction dynamics.

By Song-Lin Lv, Weiming Wu, Rui Zhu, Zi-Jian Cheng, Lan-Zhe Guo
arXiv AI
Jul 2

Persona Without Substrate: Regime-Dependence and the LLM Individuation Problem

arXiv:2607. 00006v1 Announce Type: cross Abstract: Beckmann & Butlin's (2026) ontological framework for the LLM individuation problem inherits an unargued cross-regime co-reference assumption from the persona-vectors literature: that the same direction picks out the same content under prompt-conditioning, gradient-descent fine-tuning, and inference-time steering.

By Shuaizhi Cheng