English
Related papers

Related papers: Learning How to Cube

200 papers

Large language models (LLMs) have recently demonstrated remarkable success in mathematical reasoning. Despite progress in methods like chain-of-thought prompting and self-consistency sampling, these advances often focus on final correctness…

Deep Reinforcement Learning (DRL) algorithms often require a large amount of data and struggle in sparse-reward domains with long planning horizons and multiple sub-goals. In this paper, we propose a neuro-symbolic extension of Proximal…

Artificial Intelligence · Computer Science 2026-04-29 Simone Murari , Celeste Veronese , Daniele Meli

We introduce Cube Bench, a Rubik's-cube benchmark for evaluating spatial and sequential reasoning in multimodal large language models (MLLMs). The benchmark decomposes performance into five skills: (i) reconstructing cube faces from images…

Computation and Language · Computer Science 2025-12-24 Dhruv Anand , Ehsan Shareghi

Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in their chain-of-thought reasoning. This makes the detection…

Computation and Language · Computer Science 2025-07-15 Miles Turpin , Andy Arditi , Marvin Li , Joe Benton , Julian Michael

Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being supervised, SFT is inherently limited by its generative…

Computation and Language · Computer Science 2025-07-25 Siqi Guo , Ilgee Hong , Vicente Balmaseda , Changlong Yu , Liang Qiu , Xin Liu , Haoming Jiang , Tuo Zhao , Tianbao Yang

Large language models (LLMs) have shown remarkable abilities in diverse natural language processing (NLP) tasks. The LLMs generally undergo supervised fine-tuning (SFT) followed by preference alignment to be usable in downstream…

Computation and Language · Computer Science 2024-06-27 Shiva Kumar Pentyala , Zhichao Wang , Bin Bi , Kiran Ramnath , Xiang-Bo Mao , Regunathan Radhakrishnan , Sitaram Asur , Na , Cheng

Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffers from limited generalization, while the latter, despite its…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Daoan Zhang , Guangchen Lan , Dong-Jun Han , Wenlin Yao , Xiaoman Pan , Hongming Zhang , Mingxiao Li , Pengcheng Chen , Yu Dong , Christopher Brinton , Jiebo Luo

Large language models (LLMs) have shown remarkable performance in various domains, but they are constrained by massive computational and storage costs. Quantization, an effective technique for compressing models to fit resource-limited…

Computation and Language · Computer Science 2026-04-14 Han Liu , Haotian Gao , Xiaotong Zhang , Changya Li , Feng Zhang , Wei Wang , Fenglong Ma , Hong Yu

Machine Learning algorithms have been extensively researched throughout the last decade, leading to unprecedented advances in a broad range of applications, such as image classification and reconstruction, object recognition, and text…

Artificial Intelligence · Computer Science 2022-12-20 Gustavo H. de Rosa , Mateus Roder , João Paulo Papa , Claudio F. G. dos Santos

Tasks where the set of possible actions depend discontinuously on the state pose a significant challenge for current reinforcement learning algorithms. For example, a locked door must be first unlocked, and then the handle turned before the…

Robotics · Computer Science 2023-03-09 Mrinal Verghese , Chris Atkeson

Pragmatics, the ability to infer meaning beyond literal interpretation, is crucial for social cognition and communication. While LLMs have been benchmarked for their pragmatic understanding, improving their performance remains…

Computation and Language · Computer Science 2025-06-17 Settaluri Lakshmi Sravanthi , Kishan Maharaj , Sravani Gunnu , Abhijit Mishra , Pushpak Bhattacharyya

The application of deep learning models in medical diagnosis has showcased considerable efficacy in recent years. Nevertheless, a notable limitation involves the inherent lack of explainability during decision-making processes. This study…

Image and Video Processing · Electrical Eng. & Systems 2024-05-01 Konstantinos Pasvantis , Eftychios Protopapadakis

We present MetricBERT, a BERT-based model that learns to embed text under a well-defined similarity metric while simultaneously adhering to the ``traditional'' masked-language task. We focus on downstream tasks of learning similarities for…

Computation and Language · Computer Science 2022-08-16 Itzik Malkiel , Dvir Ginzburg , Oren Barkan , Avi Caciularu , Yoni Weill , Noam Koenigstein

The pre-ranking stage plays a pivotal role in large-scale recommender systems but faces an intrinsic trade-off between model expressiveness and computational efficiency. Owing to the massive candidate pool and strict latency constraints,…

Information Retrieval · Computer Science 2025-10-29 Yutian Xiao , Meng Yuan , Fuzhen Zhuang , Wei Chen , Shukuan Wang , Shanqi Liu , Chao Feng , Wenhui Yu , Xiang Li , Lantao Hu , Han Li , Zhao Zhang

Parallel reasoning enhances Large Reasoning Models (LRMs) but incurs prohibitive costs due to futile paths caused by early errors. To mitigate this, path pruning at the prefix level is essential, yet existing research remains fragmented…

Computation and Language · Computer Science 2026-04-20 Jiaxi Bi , Tongxu Luo , Wenyu Du , Zhengyang Tang , Benyou Wang

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

Machine Learning · Computer Science 2025-12-22 Mingyu Su , Jian Guan , Yuxian Gu , Minlie Huang , Hongning Wang

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

Legal reasoning tasks present unique challenges for large language models (LLMs) due to the complexity of domain-specific knowledge and reasoning processes. This paper investigates how effectively smaller language models (Llama 2 7B and…

Machine Learning · Computer Science 2025-04-08 Rean Fernandes , André Biedenkapp , Frank Hutter , Noor Awad

Recently, transformer has achieved remarkable performance on a variety of computer vision applications. Compared with mainstream convolutional neural networks, vision transformers are often of sophisticated architectures for extracting…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Zhenhua Liu , Yunhe Wang , Kai Han , Siwei Ma , Wen Gao

We propose a new benchmark evaluating the performance of multimodal large language models on rebus puzzles. The dataset covers 333 original examples of image-based wordplay, cluing 13 categories such as movies, composers, major cities, and…