Hao Wang

SSR: Socratic Self-Refine for Large Language Model Reasoning

Haizhou Shi, Ye Liu, Bo Pang, Zeyu Liu et autres

Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, yet existing test-time frameworks often rely on coarse self-verification and self-correction, limiting their effectiveness on complex tasks. In this paper, we propose Socratic Self-Refine (SSR), a novel framework for fine-grained evaluation and precise …

TIBSTC-CoT: A Multi-Domain Instruction Dataset for Chain-of-Thought Reasoning in Language Models

Fan Gao, Cheng Huang, Nyima Tashi, Xiangxiang Wang et autres

To address the severe data scarcity in Tibetan, a low-resource language spoken by over six million people, we introduce TIBSTC-CoT, the large-scale, multi-domain Tibetan dataset automatically constructed via chain-of-thought prompting with large language models (LLMs). TIBSTC-CoT establishes a scalable and reproducible framework …

GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEs

Kalliopi Basioti, Pritish Kumar Sahu, Q. Liu, Zihao Xu et autres

Raven's Progressive Matrices (RPMs) is an established benchmark to examine the ability to perform high-level abstract visual reasoning (AVR). Despite the current success of algorithms that solve this task, humans can generalize beyond a given puzzle and create new puzzles given a …

Applications of natural language processing and large language models in materials discovery

Xue Feng Jiang, Weiren Wang, Shaohan Tian, Hao Wang et autres

The transformative impact of artificial intelligence (AI) technologies on materials science has revolutionized the study of materials problems. By leveraging well-characterized datasets derived from the scientific literature, AI-powered tools such as Natural Language Processing (NLP) have opened new avenues to accelerate materials …

cn, us (code pays fourni par la source)

Roadmap on Neuromorphic Photonics

Daniel Brunner, Bhavin J. Shastri, Mohammed Qadasi, Hitesh Ballani et autres

This roadmap consolidates recent advances while exploring emerging applications, reflecting the remarkable diversity of hardware platforms, neuromorphic concepts, and implementation philosophies reported in the field. It emphasizes the critical role of cross-disciplinary collaboration in this rapidly evolving field.

fr, be, de, us, ca (code pays fourni par la source)

CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors

Mingyuan Li, Tong Jia, Hao Wang, Bowen Ma et autres

Prohibited item detection based on X-ray images is one of the most effective security inspection methods. However, the foreground-background feature coupling caused by the overlapping phenomenon specific to X-ray images makes general detectors designed for natural images perform poorly. To address this …

mx, gb (code pays fourni par la source)

TLUE: A Tibetan Language Understanding Evaluation Benchmark

Fan Gao, Cheng Huang, Yutong Liu, Nyima Tashi et autres

Fan Gao, Cheng Huang, Yutong Liu, Nyima Tashi, Xiangxiang Wang, Thupten Tsering, Ban Ma-bao, Renzeng Duojie, Gadeng Luosang, Rinchen Dongrub, Dorje Tashi, Xiao Feng Cd, Yongbin Yu, Hao Wang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

cn, us (code pays fourni par la source)

BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models

Xinyuan Wang, Victor Shea-Jay Huang, Renmiao Chen, Hao Wang et autres

While large language models (LLMs) exhibit remarkable capabilities across various tasks, they encounter potential security risks such as jailbreak attacks, which exploit vulnerabilities to bypass security measures and generate harmful outputs. Existing jailbreak strategies mainly focus on maximizing attack success rate (ASR), …

Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition

Ye Bai, Jingping Chen, Jitong Chen, Wei Chen et autres

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios. Classic end-to-end models fused with extra language models perform well, but mainly in …

FedCoSR: Personalized Federated Learning with Contrastive Shareable Representations for Label Heterogeneity in Non-IID Data

Chenghao Huang, Xiaolu Chen, Yanru Zhang, Hao Wang

Heterogeneity arising from label distribution skew and data scarcity can cause inaccuracy and unfairness in intelligent communication applications that heavily rely on distributed computing. To deal with it, this paper proposes a novel personalized federated learning algorithm, named Federated Contrastive Shareable Representations …

A decomposition-guided mechanism for nonstationary time series forecasting

Hao Wang, Lubna Al Tarawneh, Changqing Cheng, Yu Jin

Time series forecasting has been playing an important role in decision making, control, and monitoring across various fields. Specifically, the forecasting of nonstationarity time series remains a challenging problem where traditional time series modeling may not fully capture temporal dynamics. Recent studies …

us (code pays fourni par la source)

Chinese grammatical error diagnosis based on sequence tagging methods

Hao Wang, Yuxuan Zhang, Xueliang Sun

Abstract In view of the problems such as exploding gradient or vanishing gradient or inefficiency caused by parallel problems when traditional neural networks deal with long text grammar error correction. In this paper, Chinese grammatical error detection is proposed as a sequence …

cn (code pays fourni par la source)