Fine-tuning and adaptation

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

8,201 stories · RSS feed

arXiv AI

Oct 7

Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks

arXiv:2603.04364v2 Announce Type: replace-cross Abstract: Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet th...

By Haoyu Liu, Dingcheng Li, Lukas Rutishauser, Zeyu Zheng

agents reinforcement-learning fine-tuning multimodal safety

arXiv AI

Oct 7

Federated Mixture-of-Experts Alignment on Mobile Edge Networks under Data Heterogeneity

arXiv:2603.21276v2 Announce Type: replace-cross Abstract: The growing demand for on-device large language model (LLM) services on mobile edge devices has driven the adoption of Mixture-of-Experts (Mo...

By Zihan Fang, Qianru Wang, Haonan An, Zheng Lin, Yiqin Deng, Symeon Chatzinotas, Yuguang Fang

llms fine-tuning benchmarks safety

arXiv AI

Oct 7

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?

arXiv:2605.30557v2 Announce Type: replace-cross Abstract: Spatial reasoning benchmarks typically evaluate whether vision-language models can derive the correct answer from a visual observation. Yet i...

By Yue Zhang, Zun Wang, Han Lin, Yonatan Bitton, Idan Szpektor, Mohit Bansal

llms fine-tuning multimodal benchmarks

arXiv AI

Oct 7

More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding

arXiv:2610.04753v2 Announce Type: replace-cross Abstract: Autoregressive generation in Large Language Models (LLMs) is constrained by the memory and computational demands of attention mechanisms. Spa...

By Noam Elata, Itay Lamprecht, Mikey Shechter, Daniel Ohayon, Itay Hubara, Daniel Soudry

llms fine-tuning efficiency benchmarks

arXiv Machine Learning

Oct 7

Reward-Driven Learning under Prompt-Level Differential Privacy

arXiv:2610.07212v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) trains a language model on problems that may themselves be confidential, and the trained model ca...

By Jiachen Zhao, Antonia Januszewicz, Taeho Jung

llms reinforcement-learning fine-tuning safety

arXiv Machine Learning

Oct 7

Benchmarking Time Series Foundation Models for Load Forecasting Under Covariate Uncertainty

arXiv:2610.07232v1 Announce Type: new Abstract: Accurate short-term load forecasting (STLF) is essential for the reliable and efficient operation of modern power systems. While time series foundation...

By Tomas Kaljevic, Ivan Arzola, Yu Zhang

fine-tuning benchmarks

arXiv Machine Learning

Oct 7

Weight Oracles: Reading Neural Network Weights with Language Models

arXiv:2610.07334v1 Announce Type: new Abstract: Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specific forward passes, requiring kn...

By Krishna Kabra, Constantin Venhoff, Christian Schroeder de Witt

llms fine-tuning safety

arXiv Machine Learning

Oct 7

Adapting to Changes in Agent Behavior via Finite-Depth Policy Sensitivity

arXiv:2610.07475v1 Announce Type: new Abstract: Adapting a reinforcement learning policy to changes in another agent's behavior typically requires a large amount of new interaction data. Policy sensi...

By Lan Shi, Daigo Shishika, Xuan Wang

agents reinforcement-learning fine-tuning

arXiv Machine Learning

Oct 7

$\alpha$Transfer: Coefficient Transfer for Efficient Model Merging

arXiv:2610.07819v1 Announce Type: new Abstract: Model merging offers a promising solution for combining multiple fine-tuned checkpoints into a single model through parameter arithmetic. However, find...

By Shih-Cheng Huang, Zhi Rui Tam, Chieh-Yen Lin, Yun-Nung Chen, Hung-yi Lee, Shao-Hua Sun

llms fine-tuning

arXiv Machine Learning

Oct 7

A Riemannian Geometry for Low-rank Adaptation

arXiv:2610.08049v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) is widely used as a parameter-efficient fine-tuning technique for pre-trained deep neural networks, which approximates the w...

By Shoichiro Takeda, Shin'ya Yamaguchi, Satoshi Suzuki, Yasunori Akagi

fine-tuning

arXiv Machine Learning

Oct 7

Enhancing Diffusion Language Models with Autoregressive Post-Training Weights

arXiv:2610.08108v1 Announce Type: new Abstract: Diffusion language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) language models, offering flexible token-update orders...

By Yiming Qin, Ke Wang, Amel Abdelraheem, Adam Hazimeh, Pascal Frossard

llms diffusion reinforcement-learning fine-tuning

arXiv Machine Learning

Oct 7

BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation

arXiv:2610.07594v1 Announce Type: cross Abstract: Humanoid household manipulation requires the arms to act while the body balances, steps and changes posture. We present BiGym 2.0, an adaptation of B...

By Zexi Zhang, Zecheng Zhu, Zidong Chen, Zulkhuu Tuya, Stephen James

agents reinforcement-learning robotics fine-tuning multimodal benchmarks

arXiv Machine Learning

Oct 7

Learning Grasp Targeting from Point Clouds for Log Pile Clearing on a Hydraulic Crane

arXiv:2610.07613v1 Announce Type: cross Abstract: In mill yards, log loaders clear dense piles by a sequence of bundle grasps: hundreds of logs rest in contact, and each removal changes the pile avai...

By George Sideris, Lucas Bessai, Heshan Fernando, Elie Ayoub, Nicolas Lemieux, Inna Sharf

reinforcement-learning fine-tuning

arXiv Machine Learning

Oct 7

Energy-Aware Path Following: Comparative Analysis of Reinforcement Learning and NMPC for Electric Vehicles

arXiv:2610.08112v1 Announce Type: cross Abstract: Path-following control strategies typically follow the bi-objective optimization dilemma: minimizing deviations from a reference path while maintaini...

By Mohamed Sabaa, Mostafa Emam

reinforcement-learning fine-tuning

arXiv Machine Learning

Oct 7

When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting

arXiv:2610.08718v1 Announce Type: cross Abstract: Knowledge that a language model appears to forget during finetuning often remains stored and can be recovered, a phenomenon called spurious forgettin...

By Vedant Palit, Florent Draye, Nicolas Zucchet, Zhijing Jin, Bernhard Sch\"olkopf

llms fine-tuning

arXiv Machine Learning

Oct 7

SeedER: Seed-Expand-Retrieve for Efficient Knowledge Graph Retrieval

arXiv:2605.23753v2 Announce Type: replace Abstract: Knowledge graphs (KGs) offer a rich representation for relational knowledge, but their irregular structure makes retrieval challenging: ego-graph e...

By Hamed Shirzad, Frederik Wenkel, Dominique Beaini, Danica J. Sutherland, Emmanuel Noutahi

llms rag agents reinforcement-learning fine-tuning

arXiv Machine Learning

Oct 7

PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction

arXiv:2609.34054v2 Announce Type: replace Abstract: Multi-LoRA agent systems enable efficient role specialization by sharing a common backbone model. However, each agent repeatedly processes the grow...

By Hyesung Jeon, Hyeongju Ha, Jae-Joon Kim

agents fine-tuning efficiency benchmarks

arXiv Machine Learning

Oct 7

Uncovering Cross-Objective Interference in Multi-Objective Alignment

arXiv:2602.06869v3 Announce Type: replace-cross Abstract: We study a persistent failure mode in multi-objective alignment for large language models (LLMs), in which scalarized training improves only...

By Yining Lu, Meng Jiang

llms fine-tuning safety

arXiv Machine Learning

Oct 7

Generalizable Dense Reward for Long-Horizon Robotic Tasks

arXiv:2604.00055v2 Announce Type: replace-cross Abstract: Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilit...

By Silong Yong, Stephen Sheng, Carl Qi, Xiaojie Wang, Evan Sheehan, Anurag Shivaprasad, Yaqi Xie, Katia Sycara, Yesh Dattatreya

llms reinforcement-learning robotics fine-tuning multimodal benchmarks

arXiv Computation and Language

Oct 7

Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State Machine

arXiv:2610.07070v1 Announce Type: new Abstract: Small language models are inexpensive to serve and can run on private infrastructure, but base models are often not good enough at multi-turn tool call...

By Aaron Fainman, Gabriela Kadlecov\'a, Maciej Gryka, Bartosz Kruszczy\'nski, Usman Zafar, C\'edric Archambeau, Aaron Klein, David Salinas, Selim Nowicki, Jacek Golebiowski

llms agents fine-tuning data-engineering

Get the daily briefing