中文
相关论文

相关论文: Calibrating Concepts and Operations: Towards Symbo…

200 篇论文

Reasoning capability is pivotal for Large Language Models (LLMs) to solve complex tasks, yet achieving reliable and scalable reasoning remains challenging. While Chain-of-Thought (CoT) prompting has become a mainstream approach, existing…

计算与语言 · 计算机科学 2025-10-07 Honglin Lin , Qizhi Pei , Xin Gao , Zhuoshi Pan , Yu Li , Juntao Li , Conghui He , Lijun Wu

Recent advancements in Multimodal Large Language Models (MLLMs) have incentivized models to ``think with images'' by actively invoking visual tools during multi-turn reasoning. The common Reinforcement Learning (RL) practice of relying on…

计算机视觉与模式识别 · 计算机科学 2026-04-09 Wenhao Yang , Yu Xia , Jinlong Huang , Shiyin Lu , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang , Yuchen Zhou , Xiaobo Xia , Yuanyu Wan , Lijun Zhang , Tat-Seng Chua

Recent works in image captioning have shown very promising raw performance. However, we realize that most of these encoder-decoder style networks with attention do not scale naturally to large vocabulary size, making them difficult to be…

计算机视觉与模式识别 · 计算机科学 2019-06-13 Jia Huei Tan , Chee Seng Chan , Joon Huang Chuah

Composed Image Retrieval (CIR), which aims to find a target image from a reference image and a modification text, presents the core challenge of performing unified reasoning across visual and semantic modalities. While current approaches…

计算机视觉与模式识别 · 计算机科学 2025-10-10 Weihuang Lin , Yiwei Ma , Jiayi Ji , Xiaoshuai Sun , Rongrong Ji

Recent trends in NLP aim to improve reasoning capabilities in Large Language Models (LLMs), with key focus on generalization and robustness to variations in tasks. Counterfactual task variants introduce minimal but semantically meaningful…

计算与语言 · 计算机科学 2025-11-11 Hannah Bansal , Kemal Kurniawan , Lea Frermann

In the ongoing quest for hybridizing discrete reasoning with neural nets, there is an increasing interest in neural architectures that can learn how to solve discrete reasoning or optimization problems from natural inputs, a task that Large…

人工智能 · 计算机科学 2025-12-19 Marianne Defresne , Romain Gambardella , Sophie Barbe , Thomas Schiex

The following three factors restrict the application of existing low-light image enhancement methods: unpredictable brightness degradation and noise, inherent gap between metric-favorable and visual-friendly versions, and the limited paired…

计算机视觉与模式识别 · 计算机科学 2023-08-23 Shuzhou Yang , Moxuan Ding , Yanmin Wu , Zihan Li , Jian Zhang

A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…

多智能体系统 · 计算机科学 2026-03-18 Churong Liang , Jinling Gan , Kairan Hong , Qiushi Tian , Zongze Wu , Runnan Li

Comparing different neural network representations and determining how representations evolve over time remain challenging open questions in our understanding of the function of neural networks. Comparing representations in neural networks…

机器学习 · 统计学 2018-10-25 Ari S. Morcos , Maithra Raghu , Samy Bengio

Chain-of-Thought (CoT) prompting has proven highly effective for enhancing complex reasoning in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Yet, it struggles in complex spatial reasoning tasks. Nonetheless,…

计算与语言 · 计算机科学 2025-01-14 Chengzu Li , Wenshan Wu , Huanyu Zhang , Yan Xia , Shaoguang Mao , Li Dong , Ivan Vulić , Furu Wei

The human brain is naturally equipped to comprehend and interpret visual information rapidly. When confronted with complex problems or concepts, we use flowcharts, sketches, and diagrams to aid our thought process. Leveraging this inherent…

计算机视觉与模式识别 · 计算机科学 2023-11-17 Fanxu Meng , Haotong Yang , Yiding Wang , Muhan Zhang

Neurosymbolic AI is an emerging compositional paradigm that fuses neural learning with symbolic reasoning to enhance the transparency, interpretability, and trustworthiness of AI. It also exhibits higher data efficiency making it promising…

硬件体系结构 · 计算机科学 2025-03-18 Zishen Wan , Hanchen Yang , Ritik Raj , Che-Kai Liu , Ananda Samajdar , Arijit Raychowdhury , Tushar Krishna

The recent developments and growing interest in neural-symbolic models has shown that hybrid approaches can offer richer models for Artificial Intelligence. The integration of effective relational learning and reasoning methods is one of…

机器学习 · 计算机科学 2020-05-07 Henrique Lemos , Pedro Avelar , Marcelo Prates , Luís Lamb , Artur Garcez

For vision-and-language reasoning tasks, both fully connectionist, end-to-end methods and hybrid, neuro-symbolic methods have achieved high in-distribution performance. In which out-of-distribution settings does each paradigm excel? We…

计算与语言 · 计算机科学 2022-10-28 Wang Zhu , Jesse Thomason , Robin Jia

Computational modeling and simulation have become essential tools in the quest to better understand the brain's makeup and to decipher the causal interrelations of its components. The breadth of biochemical and biophysical processes and…

神经元与认知 · 定量生物学 2019-06-10 Francesco Cremonesi , Felix Schürmann

Language models' (LMs) proficiency in handling deterministic symbolic reasoning and rule-based tasks remains limited due to their dependency implicit learning on textual data. To endow LMs with genuine rule comprehension abilities, we…

计算与语言 · 计算机科学 2024-03-12 Yixuan Weng , Minjun Zhu , Fei Xia , Bin Li , Shizhu He , Kang Liu , Jun Zhao

Complex Query Answering (CQA) is a crucial reasoning task over Knowledge Graphs (KGs), which aims to answer first-order logical queries from incomplete KGs. While existing neural-symbolic methods achieve strong performance, they face…

人工智能 · 计算机科学 2026-05-26 Weizhi Fei , Zihao Wang , hang Yin , Shukai Zhao , Wei Zhang , Yangqiu Song

Recent multimodal large language models (MLLMs) increasingly rely on visual chain-of-thought to perform region-grounded reasoning over images. However, existing approaches ground regions via either textified coordinates-causing modality…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Kesen Zhao , Beier Zhu , Junbao Zhou , Xingyu Zhu , Zhongqi Yue , Hanwang Zhang

Chain-of-thought (CoT) reasoning has exhibited impressive performance in language models for solving complex tasks and answering questions. However, many real-world questions require multi-modal information, such as text and images.…

人工智能 · 计算机科学 2023-12-15 Liqi He , Zuchao Li , Xiantao Cai , Ping Wang

Contributions to AI: This paper proposes a neuro-symbolic search architecture integrating discrete rule-based logic with lightweight Neural Network Feedback Control (NNFC). Utilizing cascade filtering to isolate neural mispredictions while…

软件工程 · 计算机科学 2026-03-27 Jipeng Han