English
Related papers

Related papers: When to Stop Reusing: Dynamic Gradient Gating for …

200 papers

Forward gradient descent (FGD) has been proposed as a biologically more plausible alternative of gradient descent as it can be computed without backward pass. Considering the linear model with $d$ parameters, previous work has found that…

Statistics Theory · Mathematics 2024-11-27 Niklas Dexheimer , Johannes Schmidt-Hieber

Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Generation (RAG) enriches prompts with external information, but…

Computation and Language · Computer Science 2025-10-02 Oussama Gabouj , Kamel Charaf , Ivan Zakazov , Nicolas Baldwin , Robert West

The most advanced diffusion models have recently adopted increasingly deep stacked networks (e.g., U-Net or Transformer) to promote the generative emergence capabilities of vision generation models similar to large language models (LLMs).…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Zhiyuan Ma , Liangliang Zhao , Biqing Qi , Bowen Zhou

Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed a leap in Large Language Model (LLM) reasoning, yet its optimization dynamics remain fragile. Standard algorithms like GRPO enforce stability via "hard clipping", which…

Machine Learning · Computer Science 2026-04-21 Xiaoliang Fu , Jiaye Lin , Yangyi Fang , Chaowen Hu , Cong Qin , Zekai Shao , Binbin Zheng , Lu Pan , Ke Zeng

Retrieval-Augmented Generation (RAG) has proven its effectiveness in mitigating hallucinations in Large Language Models (LLMs) by retrieving knowledge from external resources. To adapt LLMs for the RAG systems, current approaches use…

Computation and Language · Computer Science 2025-03-05 Xinze Li , Sen Mei , Zhenghao Liu , Yukun Yan , Shuo Wang , Shi Yu , Zheni Zeng , Hao Chen , Ge Yu , Zhiyuan Liu , Maosong Sun , Chenyan Xiong

Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant breakthroughs in complex LLM reasoning within verifiable domains, such as mathematics and programming. Recent efforts have sought to extend this paradigm to…

Machine Learning · Computer Science 2026-02-03 Zheng Zhang , Ao Lu , Yuanhao Zeng , Ziwei Shan , Jinjin Guo , Lufei Li , Yexin Li , Kan Ren

Reinforcement learning (RL) has emerged as an effective post-training paradigm for enhancing the reasoning capabilities of multimodal large language model (MLLM). However, current RL pipelines often suffer from training inefficiencies…

Machine Learning · Computer Science 2026-03-04 Linghao Zhu , Yiran Guan , Dingkang Liang , Jianzhong Ju , Zhenbo Luo , Bin Qin , Jian Luan , Yuliang Liu , Xiang Bai

We consider a distributed learning problem in which the computation is carried out on a system consisting of a master node and multiple worker nodes. In such systems, the existence of slow-running machines called stragglers will cause a…

Information Theory · Computer Science 2019-01-16 Shunsuke Horii , Takahiro Yoshida , Manabu Kobayashi , Toshiyasu Matsushima

This paper presents a novel neural network training approach for faster convergence and better generalization abilities in deep reinforcement learning. Particularly, we focus on the enhancement of training and evaluation performance in…

Machine Learning · Computer Science 2020-05-26 Mohammed Sharafath Abdul Hameed , Gavneet Singh Chadha , Andreas Schwung , Steven X. Ding

The composition of training data mixtures is critical for effectively training large language models (LLMs), as it directly impacts their performance on downstream tasks. Our goal is to identify an optimal data mixture to specialize an LLM…

Machine Learning · Computer Science 2024-10-04 Simin Fan , David Grangier , Pierre Ablin

Large Language Models (LLMs) have demonstrated remarkable proficiency in vulnerability detection. However, a critical reliability gap persists: models frequently yield correct detection verdicts based on hallucinated logic or superficial…

Cryptography and Security · Computer Science 2026-02-09 Li Lu , Yanjie Zhao , Hongzhou Rao , Kechi Zhang , Haoyu Wang

Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue that many headline RLVR gains are not yet well validated…

Rerandomization is an experimental design technique that repeatedly randomizes treatment assignments until covariates are balanced between treatment groups. Rerandomization in the design stage of an experiment can lead to many asymptotic…

Methodology · Statistics 2026-04-10 Antônio Carlos Herling Ribeiro Junior

Stochastic gradient descent (SGD) provides a simple and efficient way to solve a broad range of machine learning problems. Here, we focus on distribution regression (DR), involving two stages of sampling: Firstly, we regress from…

Machine Learning · Statistics 2021-03-08 Nicole Mücke

Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs). A common problem is reward hacking, where the policy may exploit inaccuracies of the…

Machine Learning · Computer Science 2026-02-23 Johannes Ackermann , Michael Noukhovitch , Takashi Ishida , Masashi Sugiyama

Reinforcement learning with verifiers (RLVR) is a central paradigm for improving large language model (LLM) reasoning, yet existing methods often suffer from limited exploration. Policies tend to collapse onto a few reasoning patterns and…

Machine Learning · Computer Science 2026-02-24 Zhongwei Wan , Yun Shen , Zhihao Dou , Donghao Zhou , Yu Zhang , Xin Wang , Hui Shen , Jing Xiong , Chaofan Tao , Zixuan Zhong , Peizhou Huang , Mi Zhang

Stochastic Gradient Descent (SGD) is a fundamental algorithm in machine learning, representing the optimization backbone for training several classic models, from regression to neural networks. Given the recent practical focus on…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-06-25 Dan Alistarh , Christopher De Sa , Nikola Konstantinov

Multi-Task Learning (MTL) has achieved success in various fields. However, how to balance different tasks to achieve good performance is a key problem. To achieve the task balancing, there are many works to carefully design dynamical…

Machine Learning · Computer Science 2022-07-28 Baijiong Lin , Feiyang Ye , Yu Zhang , Ivor W. Tsang

Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods utilize rollouts in an indiscriminate and short-horizon manner:…

Machine Learning · Computer Science 2026-05-26 Xiaodong Lu , Xiaohan Wang , Jiajun Chai , Guojun Yin , Wei Lin , Zhijun Chen , Yu Luo , Fuzhen Zhuang , Yikun Ban , Deqing Wang

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge, yielding relevance responses that are aligned with factual evidence and evolving corpora. Standard RAG pipelines…

Machine Learning · Computer Science 2026-04-07 Xun Sun , Baiheng Xie , Li Huang , Qiang Gao