Fine-tuning and adaptation

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

8,248 stories · RSS feed

arXiv AI

Jun 11

On the Study of Biometric Spoofing Detection using Deep Learning

arXiv:2606. 11505v1 Announce Type: cross Abstract: Biometric systems are increasingly deployed in security applications; however, they remain vulnerable to spoofing attacks, in which attackers exploit counterfeit biometric data to gain unauthorized access.

By Kumar Kartikey, Nikos Komninos

fine-tuning benchmarks

arXiv Machine Learning

Jun 11

Coverage Guarantees for Pseudo-Calibrated Conformal Prediction under Distribution Shift

arXiv:2602. 14913v2 Announce Type: replace Abstract: Conformal prediction (CP) offers distribution-free marginal coverage guarantees under an exchangeability assumption, but these guarantees can fail if the data distribution shifts.

By Farbod Siahkali, Ashwin Verma, Vijay Gupta

fine-tuning

arXiv AI

Jun 11

When Roleplaying, Do Models Believe What They Say?

arXiv:2606. 11502v1 Announce Type: cross Abstract: Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite.

By Benjamin Sturgeon, David Africa, Sid Black

llms fine-tuning

arXiv Machine Learning

Jun 11

Mechanisms of Introspective Awareness

arXiv:2603. 21396v5 Announce Type: replace Abstract: Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness.

By Uzay Macar, Li Yang, Atticus Wang, Peter Wallich, Emmanuel Ameisen, Jack Lindsey

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jun 11

Grounding Computer Use Agents on Human Demonstrations

arXiv:2511. 07332v2 Announce Type: replace-cross Abstract: Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements.

By Aarash Feizi, Shravan Nayak, Xiangru Jian, Kevin Qinghong Lin, Kaixin Li, Rabiul Awal, Xing Han L\`u, Johan Obando-Ceron, Juan A. Rodriguez, Nicolas Chapados, David Vazquez, Adriana Romero-Soriano, Reihaneh Rabbany, Perouz Taslakian, Christopher Pal, Spandana Gella, Sai Rajeswar

agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 11

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

arXiv:2606. 11324v1 Announce Type: cross Abstract: We introduce Embodied-R1.

By Yifu Yuan, Yaoting Huang, Xianze Yao, Yutong Li, Shuoheng Zhang, Linqi Han, Pengyi Li, Jiangeng Sun, Wenting Jia, Zhao Zhang, Yuhao Liu, Ruihao Liao, Yucheng Hu, Qiyu Wu, Yuxiao Li, Zibin Dong, Fei Ni, Yan Zheng, Shuyang Gu, Yi Ma, Hongyao Tang, Han Hu, Jianye Hao

llms reinforcement-learning robotics fine-tuning multimodal benchmarks

arXiv Machine Learning

Jun 11

Point-Identification of a Robust Predictor Under Latent Shift with Imperfect Proxies

arXiv:2603. 15158v2 Announce Type: replace Abstract: Addressing the domain adaptation problem becomes more challenging when distribution shifts across domains stem from latent confounders that affect both covariates and outcomes.

By Zahra Rahiminasab, Reza Soumi, Arto Klami, Samuel Kaski

fine-tuning

arXiv AI

Jun 11

Weakly Supervised Segmentation as Semantic-Based Regularization

arXiv:2605. 13674v2 Announce Type: replace-cross Abstract: Weakly supervised semantic segmentation (WSSS) trains dense pixel-level segmentation models from partial or coarse annotations such as bounding boxes, scribbles, or image-level tags.

By Stefano Colamonaco, Andrei-Bogdan Florea, Jaron Maene

computer-vision fine-tuning benchmarks

arXiv AI

Jun 11

AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory

arXiv:2606. 11751v1 Announce Type: cross Abstract: Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successive steps.

By Hang Xu, Xiaoxiao Ma, Guohui Zhang, Yu Hu, Siming Fu, Jie Huang, Lin Song, Haoyang Huang, Nan Duan, Feng Zhao

diffusion fine-tuning efficiency benchmarks safety

arXiv AI

Jun 11

MLaGA: Multimodal Large Language and Graph Assistant

arXiv:2506. 02568v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated substantial efficacy in advancing graph-structured data analysis.

By Dongzhe Fan, Yi Fang, Jiajin Liu, Djellel Difallah, Qiaoyu Tan

llms fine-tuning multimodal

arXiv Machine Learning

Jun 11

Probabilistic Contrastive Pretraining for Multi-task ADME Property Prediction

arXiv:2606. 11508v1 Announce Type: new Abstract: Accurate prediction of absorption, distribution, metabolism, and excretion (ADME) properties is critical to drug discovery, but remains challenging because ADME endpoints are noisy, interdependent, and often data-limited.

By Yifan Xue, Srimukh Prasad Veccham, Saee Paliwal, Tyler Shimko, Micha Livne

llms fine-tuning

arXiv AI

Jun 11

Harness In-Context Operator Learning with Chain of Operators

arXiv:2606. 12318v1 Announce Type: cross Abstract: Neural operators approximate mappings between function spaces, but often generalize poorly to other operators and usually require fine-tuning or retraining.

By Minghui Yang, Ling Guo, Liu Yang

llms fine-tuning

arXiv AI

Jun 11

Bimanual Robot Manipulation via Multi-Agent In-Context Learning

arXiv:2604. 20348v2 Announce Type: replace-cross Abstract: Language Models (LLMs) have emerged as powerful reasoning engines for embodied control.

By Alessio Palma, Indro Spinelli, Vignesh Prasad, Luca Scofano, Yufeng Jin, Georgia Chalvatzaki, Fabio Galasso

llms agents robotics fine-tuning benchmarks

arXiv AI

Jun 11

PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry

arXiv:2606. 11262v1 Announce Type: cross Abstract: Access control in large language models (LLMs) requires modular mechanisms to enable domain-specific behavior without retraining or cross-domain interference.

By Gowtham Sivaramakrishnan, Sarvesha Kumar Kombaiah Seetha, Kishan Gupta Balaji, Santhosh Baradwaj Vaduvur Ranganathan

llms fine-tuning benchmarks safety

arXiv AI

Jun 11

Forecasting Future Behavior as a Learning Task

arXiv:2606. 11445v1 Announce Type: new Abstract: Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs.

By Mosh Levy, Yoav Goldberg, Asa Cooper Stickland

llms fine-tuning

arXiv AI

Jun 11

Substrate Asymmetry in User-Side Memory: A Diagnostic Framework

arXiv:2606. 11712v1 Announce Type: cross Abstract: User-side memory in LLMs is typically scored as a single "personalization" capability: given a user's history, is the output more user-aware?

By Youwang Deng

llms rag reinforcement-learning fine-tuning safety

arXiv AI

Jun 11

MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback

arXiv:2606. 07909v2 Announce Type: replace Abstract: Modern large language model (LLM) agents can use external tools to help users solve complex tasks.

By Suleyman Armagan Er, Danilo Ribeiro, Yogesh Virkar, Surafel Lakew, Adi Kalyanpur, James Gung, Thomas Delteil, Arshit Gupta

llms agents fine-tuning benchmarks

arXiv Machine Learning

Jun 11

Massive Open-Vocabulary Keyword Spotting

arXiv:2606. 11279v1 Announce Type: cross Abstract: Automatic speech recognition systems have been shown to under-perform when it comes to transcribing words rarely seen in the training data, namely specialized terminology.

By Leonor Barreiros, Raul Monteiro, Afonso Mendes, Gon\c{c}alo M. Correia

fine-tuning efficiency multimodal

arXiv AI

Jun 11

OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models

arXiv:2606. 12169v1 Announce Type: cross Abstract: High-stakes clinical use of large vision-language models (LVLMs) requires reasoning that is grounded in visual evidence and clinical knowledge, not just correct final answers.

By Negin Baghbanzadeh, Pritam Sarkar, Michael Colacci, Abeer Badawi, Adibvafa Fallahpour, Arash Afkanpour, Leonid Sigal, Ali Etemad, Elham Dolatabadi

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jun 11

The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning

arXiv:2606. 11918v1 Announce Type: new Abstract: Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks.

By Theo Uscidda, Marta Tintore Gazulla, Maks Ovsjanikov, Federico Tombari, Leonidas Guibas

reinforcement-learning fine-tuning safety

Get the daily briefing