English
Related papers

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

200 papers

Supervised Fine-Tuning (SFT) is a critical step for enhancing the instruction-following capabilities of Large Language Models (LLMs) and adapting them to specialized domains. However, SFT often leads to a degradation of the model's general…

Computation and Language · Computer Science 2025-07-01 Fei Ding , Baiqiao Wang

Recently, large language models (LLMs) and vision-language models (VLMs) have achieved significant success, demonstrating remarkable capabilities in understanding various images and videos, particularly in classification and detection…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Fei Wang , Chengcheng Chen , Hongyu Chen , Yugang Chang , Weiming Zeng

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

Computation and Language · Computer Science 2025-08-27 Junjie Ye , Yilong Wu , Sixian Li , Yuming Yang , Zhiheng Xi , Tao Gui , Qi Zhang , Xuanjing Huang , Peng Wang , Zhongchao Shi , Jianping Fan , Zhengyin Du

Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this…

Machine Learning · Computer Science 2025-12-04 Howard Chen , Noam Razin , Karthik Narasimhan , Danqi Chen

Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Haozhan Shen , Peng Liu , Jingcheng Li , Chunxin Fang , Yibo Ma , Jiajia Liao , Qiaoli Shen , Zilun Zhang , Kangjia Zhao , Qianqian Zhang , Ruochen Xu , Tiancheng Zhao

We propose a generalized method for boosting the generalization ability of pre-trained vision-language models (VLMs) while fine-tuning on downstream few-shot tasks. The idea is realized by exploiting out-of-distribution (OOD) detection to…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Kun Ding , Haojian Zhang , Qiang Yu , Ying Wang , Shiming Xiang , Chunhong Pan

Training LLMs to think and reason for longer has become a key ingredient in building state-of-the-art models that can solve complex problems previously out of reach. Recent efforts pursue this in different ways, such as RL fine-tuning to…

Machine Learning · Computer Science 2026-02-03 Yihao Xue , Allan Zhang , Jianhao Huang , Amit Sahai , Baharan Mirzasoleiman

Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when enhanced by Reinforcement Learning (RL) techniques like…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Peiyao Wang , Haotian Xu , Noranart Vesdapunt , Rui Hou , Jingyi Zhang , Haibin Ling , Oleksandr Obiednikov , Ning Zhou , Kah Kuen Fu

Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models for advanced mathematical reasoning and coding. Following the success of frontier reasoning models, recent work has demonstrated that…

Machine Learning · Computer Science 2025-08-11 Rosie Zhao , Alexandru Meterez , Sham Kakade , Cengiz Pehlevan , Samy Jelassi , Eran Malach

Deep Reinforcement Learning has shown great success in a variety of control tasks. However, it is unclear how close we are to the vision of putting Deep RL into practice to solve real world problems. In particular, common practice in the…

Machine Learning · Computer Science 2019-02-21 Chenyang Zhao , Olivier Sigaud , Freek Stulp , Timothy M. Hospedales

Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning…

Computation and Language · Computer Science 2024-06-10 Guanting Dong , Hongyi Yuan , Keming Lu , Chengpeng Li , Mingfeng Xue , Dayiheng Liu , Wei Wang , Zheng Yuan , Chang Zhou , Jingren Zhou

Vision-Language Models (VLMs) have demonstrated remarkable progress in chart understanding, largely driven by supervised fine-tuning (SFT) on increasingly large synthetic datasets. However, scaling SFT data alone is inefficient and…

Computation and Language · Computer Science 2026-05-12 Jianzhu Bao , Haozhen Zhang , Kuicai Dong , Bozhi Wu , Sarthak Ketanbhai Modi , Zi Pong Lim , Yon Shin Teo , Wenya Wang

Although supervised finetuning (SFT) has emerged as an essential technique to align large language models with humans, it is considered superficial, with style learning being its nature. At the same time, recent works indicate the…

Computation and Language · Computer Science 2024-02-12 Ming Shen

Prior research on out-of-distribution detection (OoDD) has primarily focused on single-modality models. Recently, with the advent of large-scale pretrained vision-language models such as CLIP, OoDD methods utilizing such multi-modal…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Jeonghyeon Kim , Sangheum Hwang

Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incurs substantial memory overhead. Delta compression addresses this by retaining a single…

Machine Learning · Computer Science 2026-04-21 Junlin Li , Shuangyong Song , Guodong Du , Ngai Wong , Xuebo Liu , Yongxiang Li , Min Zhang , Jing Li , Xuelong Li

Large language models (LLMs) such as GPT-4 sometimes appear to be creative, solving novel tasks often with a few demonstrations in the prompt. These tasks require the models to generalize on distributions different from those from training…

Computation and Language · Computer Science 2024-12-31 Jiajun Song , Zhuoyan Xu , Yiqiao Zhong

Generalization to novel compound tasks under distribution shift is important for deploying transformer-based language models (LMs). This work investigates Chain-of-Thought (CoT) reasoning as a means to enhance OOD generalization. Through…

Computation and Language · Computer Science 2026-03-31 Ru Wang , Wei Huang , Selena Song , Haoyu Zhang , Qian Niu , Yusuke Iwasawa , Yutaka Matsuo , Jiaxian Guo

Vision Language Models (VLMs) are impressive at visual question answering and image captioning. But they underperform on multi-step visual reasoning -- even compared to LLMs on the same tasks presented in text form -- giving rise to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Simon Park , Abhishek Panigrahi , Yun Cheng , Dingli Yu , Anirudh Goyal , Sanjeev Arora

Vision-and-language (V&L) models pretrained on large-scale multimodal data have demonstrated strong performance on various tasks such as image captioning and visual question answering (VQA). The quality of such models is commonly assessed…

Computation and Language · Computer Science 2023-04-04 Aishwarya Agrawal , Ivana Kajić , Emanuele Bugliarello , Elnaz Davoodi , Anita Gergely , Phil Blunsom , Aida Nematzadeh

Supervised and preference-based fine-tuning techniques have become popular for aligning large language models (LLMs) with user intent and correctness criteria. However, real-world training data often exhibits spurious correlations --…

Computation and Language · Computer Science 2025-05-12 Julia Shuieh , Prasann Singhal , Apaar Shanker , John Heyer , George Pu , Samuel Denton