English
Related papers

Related papers: Why Does RL Generalize Better Than SFT? A Data-Cen…

200 papers

Foundation models encode rich representations that can be adapted to downstream tasks by fine-tuning. However, fine-tuning a model on one data distribution often degrades performance under distribution shifts. Current approaches to robust…

Machine Learning · Computer Science 2024-03-15 Caroline Choi , Yoonho Lee , Annie Chen , Allan Zhou , Aditi Raghunathan , Chelsea Finn

The growing success of Vision-Language-Action (VLA) models stems from the promise that pretrained Vision-Language Models (VLMs) can endow agents with transferable world knowledge and vision-language (VL) grounding, laying a foundation for…

Machine Learning · Computer Science 2025-10-30 Nikita Kachaev , Mikhail Kolosov , Daniil Zelezetsky , Alexey K. Kovalev , Aleksandr I. Panov

Few-Shot Recognition (FSR) tackles classification tasks by training with minimal task-specific labeled data. Prevailing methods adapt or finetune a pretrained Vision-Language Model (VLM) and augment the scarce training data by retrieving…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Hanxin Wang , Tian Liu , Shu Kong

Large language models (LLMs) have achieved remarkable proficiency on solving diverse problems. However, their generalization ability is not always satisfying and the generalization problem is common for generative transformer models in…

Machine Learning · Computer Science 2024-08-20 Xingcheng Xu , Zihao Pan , Haipeng Zhang , Yanqing Yang

The reusability of state-of-the-art Pre-trained Language Models (PLMs) is often limited by their generalization problem, where their performance drastically decreases when evaluated on examples that differ from the training dataset, known…

Computation and Language · Computer Science 2023-08-09 Somayeh Ghanbarzadeh , Hamid Palangi , Yan Huang , Radames Cruz Moreno , Hamed Khanpour

General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…

Machine Learning · Computer Science 2026-03-24 Andrey Goncharov , Daniil Vyazhev , Petr Sychev , Edvard Khalafyan , Alexey Zaytsev

Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving…

Machine Learning · Computer Science 2019-03-18 Charles Packer , Katelyn Gao , Jernej Kos , Philipp Krähenbühl , Vladlen Koltun , Dawn Song

Mathematical reasoning is a challenging task for large language models (LLMs), while the scaling relationship of it with respect to LLM capacity is under-explored. In this paper, we investigate how the pre-training loss, supervised data…

Computation and Language · Computer Science 2023-09-14 Zheng Yuan , Hongyi Yuan , Chengpeng Li , Guanting Dong , Keming Lu , Chuanqi Tan , Chang Zhou , Jingren Zhou

Learning robust vision models that perform well in out-of-distribution (OOD) situations is an important task for model deployment in real-world settings. Despite extensive research in this field, many proposed methods have only shown minor…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Gyuseong Lee , Wooseok Jang , Jinhyeon Kim , Jaewoo Jung , Seungryong Kim

Existing LLMs-post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT). Each paradigm presents a distinct trade-off: (1) SFT excels at mimicking demonstration data, but can lead…

Machine Learning · Computer Science 2026-05-18 Zeyu Huang , Tianhao Cheng , Zihan Qiu , Zili Wang , Yinghui Xu , Edoardo M. Ponti , Ivan Titov

We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is mixed regarding whether training on easier or harder data…

Computation and Language · Computer Science 2025-11-27 Yeganeh Kordi , Nihal V. Nayak , Max Zuo , Ilana Nguyen , Stephen H. Bach

Reinforcement learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for eliciting reasoning capabilities in large language models, particularly in mathematics and coding. While recent efforts have extended this paradigm…

Computation and Language · Computer Science 2026-03-13 Hanxu Hu , Yuxuan Wang , Maggie Huan , Jannis Vamvas , Yinya Huang , Zhijiang Guo , Rico Sennrich

Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias can explain their lack of robustness out of distribution…

Machine Learning · Computer Science 2022-09-13 Damien Teney , Ehsan Abbasnejad , Simon Lucey , Anton van den Hengel

Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant. At the same time, SFT may harm the fundamental capabilities of an LLM,…

Machine Learning · Computer Science 2026-04-16 Mark Rofin , Aditya Varre , Nicolas Flammarion

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

Machine Learning · Computer Science 2026-01-22 Song Lai , Haohan Zhao , Rong Feng , Changyi Ma , Wenzhuo Liu , Hongbo Zhao , Xi Lin , Dong Yi , Qingfu Zhang , Hongbin Liu , Gaofeng Meng , Fei Zhu

Despite overparameterization, deep networks trained via supervised learning are easy to optimize and exhibit excellent generalization. One hypothesis to explain this is that overparameterized deep networks enjoy the benefits of implicit…

Machine Learning · Computer Science 2021-12-10 Aviral Kumar , Rishabh Agarwal , Tengyu Ma , Aaron Courville , George Tucker , Sergey Levine

Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-training methods rely on supervised fine-tuning (SFT), which…

Robotics · Computer Science 2026-03-09 Liangzhi Shi , Shuaihang Chen , Feng Gao , Yinuo Chen , Kang Chen , Tonghe Zhang , Hongzhi Zang , Weinan Zhang , Chao Yu , Yu Wang

Recent advances in vision-language models (VLMs) have improved Chest X-ray (CXR) interpretation in multiple aspects. However, many medical VLMs rely solely on supervised fine-tuning (SFT), which optimizes next-token prediction without…

Handling distribution shifts from training data, known as out-of-distribution (OOD) generalization, poses a significant challenge in the field of machine learning. While a pre-trained vision-language model like CLIP has demonstrated…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Bac Nguyen , Stefan Uhlich , Fabien Cardinaux , Lukas Mauch , Marzieh Edraki , Aaron Courville

While state-of-the-art vision-language models (VLMs) have demonstrated remarkable capabilities in complex visual-text tasks, their success heavily relies on massive model scaling, limiting their practical deployment. Small-scale VLMs offer…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Huilin Deng , Ding Zou , Rui Ma , Hongchen Luo , Yang Cao , Yu Kang