English
Related papers

Related papers: Weight Ensembling Improves Reasoning in Language M…

200 papers

Reinforcement learning substantially improves reasoning in large language models, but it also tends to lengthen chain of thought outputs and increase computational cost during both training and inference. Though length control methods have…

Computation and Language · Computer Science 2026-02-12 Daisuke Nohara , Taishi Nakamura , Rio Yokota

Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau…

Machine Learning · Computer Science 2026-04-22 Qingyang Zhang , Xinke Kong , Haitao Wu , Qinghua Hu , Minghao Wu , Baosong Yang , Yu Cheng , Yun Luo , Ganqu Cui , Changqing Zhang

Both classification and regression tasks are susceptible to the biased distribution of training data. However, existing approaches are focused on the class-imbalanced learning and cannot be applied to the problems of numerical regression…

Machine Learning · Computer Science 2021-09-15 Wentai Wu , Ligang He , Weiwei Lin

Supervised Fine-Tuning (SFT) has been a go-to and effective method for enhancing long chain-of-thought (CoT) reasoning in relatively small LLMs by fine-tuning them with long CoT responses from larger LLMs. To continually improve reasoning…

Machine Learning · Computer Science 2025-02-20 Wang Yang , Hongye Jin , Jingfeng Yang , Vipin Chaudhary , Xiaotian Han

Test-time scaling (TTS) has emerged as a powerful paradigm for improving the reasoning ability of Large Language Models (LLMs) by allocating additional computation at inference, yet its application to multimodal systems such as…

A data set sampled from a certain population is biased if the subgroups of the population are sampled at proportions that are significantly different from their underlying proportions. Training machine learning models on biased data sets…

Machine Learning · Computer Science 2021-08-30 Jing An , Lexing Ying , Yuhua Zhu

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…

Machine Learning · Computer Science 2025-10-10 Yeskendir Koishekenov , Aldo Lipani , Nicola Cancedda

We investigate parameter-efficient fine-tuning (PEFT) methods that can provide good accuracy under limited computational and memory budgets in the context of large language models (LLMs). We present a new PEFT method called Robust…

Computation and Language · Computer Science 2024-06-04 Mahdi Nikdan , Soroush Tabesh , Elvir Crnčević , Dan Alistarh

In recent years, large language models (LLMs) have demonstrated significant potential in complex reasoning tasks like mathematical problem-solving. However, existing research predominantly relies on reinforcement learning (RL) frameworks…

Machine Learning · Computer Science 2026-01-12 ShaoZhen Liu , Xinting Huang , Houwen Peng , Xin Chen , Xinyang Song , Qi Li , Zhenan Sun

In this work, we investigate the merits of explicitly optimizing for inference time algorithmic performance during model training. We show how optimizing for inference time performance can improve overall model efficacy. We consider generic…

Machine Learning · Computer Science 2025-08-19 Yunhao Tang , Kunhao Zheng , Gabriel Synnaeve , Rémi Munos

Quantum error correction requires decoders that are both accurate and efficient. To this end, union-find decoding has emerged as a promising candidate for error correction on the surface code. In this work, we benchmark a weighted variant…

Quantum Physics · Physics 2020-07-22 Shilin Huang , Michael Newman , Kenneth R. Brown

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

Machine Learning · Computer Science 2025-10-31 Fuxiang Zhang , Jiacheng Xu , Chaojie Wang , Ce Cui , Yang Liu , Bo An

Supervised fine-tuning (SFT) on chain-of-thought (CoT) trajectories demonstrations is a common approach for enabling reasoning in large language models. Standard practices typically only retain trajectories with correct final answers…

Computation and Language · Computer Science 2026-01-12 Xueyun Tian , Minghua Ma , Bingbing Xu , Nuoyan Lyu , Wei Li , Heng Dong , Zheng Chu , Yuanzhuo Wang , Huawei Shen

Standard negative log-likelihood (NLL) for Supervised Fine-Tuning (SFT) applies uniform token-level weighting. This rigidity creates a two-fold failure mode: (i) overemphasizing low-probability targets can amplify gradients on noisy…

Computation and Language · Computer Science 2026-02-13 Zecheng Wang , Deyuan Liu , Chunshan Li , Yupeng Zhang , Zhengyun Zhao , Dianhui Chu , Bingning Wang , Dianbo Sui

The democratization of ubiquitous AI hinges on deploying sophisticated reasoning capabilities on resource-constrained devices. However, Small Language Models (SLMs) often face a "reasoning gap", particularly in non-English languages like…

Computation and Language · Computer Science 2026-04-21 Bui The Trung , Do Minh Duc , Nguyen Van Vinh , Bui Nguyen Quoc Trinh

Parameter-Efficient Fine-Tuning (PEFT) is increasingly recognized as an effective method in speech processing. However, the optimal approach and the placement of PEFT methods remain inconclusive. Our study conducts extensive experiments to…

Computation and Language · Computer Science 2024-02-08 Tzu-Han Lin , How-Shing Wang , Hao-Yung Weng , Kuang-Chen Peng , Zih-Ching Chen , Hung-yi Lee

Weight pruning is widely advocated for deploying Large Language Models on resource-constrained IoT and edge devices, yet its impact on model fairness remains poorly understood. We conduct a controlled empirical study of three…

Machine Learning · Computer Science 2026-05-12 Plawan Kumar Rath , Rahul Maliakkal

Simulated tempering is popular method of allowing MCMC algorithms to move between modes of a multimodal target density {\pi}. One problem with simulated tempering for multimodal targets is that the weights of the various modes change for…

Computation · Statistics 2019-02-12 Nicholas G. Tawn , Gareth O. Roberts , Jeffrey S. Rosenthal

Widely used language models (LMs) are typically built by scaling up a two-stage training pipeline: a pre-training stage that uses a very large, diverse dataset of text and a fine-tuning (sometimes, 'alignment') stage that uses targeted…

Computation and Language · Computer Science 2023-10-20 Eric Mitchell , Rafael Rafailov , Archit Sharma , Chelsea Finn , Christopher D. Manning

Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting - a dominant format for multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Jiahao Wang , Weiye Xu , Aijun Yang , Wengang Zhou , Lewei Lu , Houqiang Li , Xiaohua Wang , Jinguo Zhu
‹ Prev 1 8 9 10 Next ›