Selective Contrastive Learning For Gloss Free Sign Language Translation
School of Informatics, Xiamen University, China(厦门大学信息学院);Key Lab of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian-Taiwan (XMU), Ministry of Culture and Tourism, China(福建省 Fujian-Taiwan 非物质文化遗产数字保护与智能处理重点实验室,文化部,中国);National Language Resources Monitoring and Research Center for Education and Teaching Media, Xiamen University, China(教育与教学媒体语言资源监测与研究中心,厦门大学,中国)
Changhao Lai, Rui Zhao, Xuewen Zhong, Jinsong Su, Yidong Chen
Sign language translation (SLT) converts continuous sign videos into spoken-language text, yet it remains challenging due to the intrinsic modality mismatch between visual signs and written text, particularly in gloss-free settings. Recent SLT systems increasingly adopt CLIP-like Vision-Language pretraining (VLP) for cross-modal alignment, but the random in-batch contrast provides few, batch-dependent negatives and may mislabel semantically similar (or even identical) pairs as negatives, introducing noisy and potentially inconsistent alignment supervision. In this work, we first conduct a preliminary trajectory-based analysis that tracks negative video-text similarity over training. The results show that only a small subset of negatives exhibits the desired behavior of being consistently pushed away, while the remaining negatives display heterogeneous and often non-decreasing similarity dynamics, suggesting that random in-batch negatives are frequently uninformative for effective alignment. Inspired by this, we propose Selective Contrastive Learning for SLT (SCL-SLT) with a Pair Selection (PS) strategy. PS scores candidate negatives using similarity dynamics from reference checkpoints and constructs mini-batches via a curriculum that progressively emphasizes more challenging negatives, thereby strengthening contrastive supervision while reducing the influence of noisy or semantically invalid negatives.
G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment
NLP 2 CT Lab, Department of Computer and Information Science, University of Macau(NLP 2 CT实验室,计算机与信息科学系,澳门大学);Faculty of Arts and Humanities, University of Macau(人文学院,澳门大学)
Improving Gloss-free Sign Language Translation by Reducing Representation Density
Artificial Intelligence Thrust, HKUST (Guangzhou)(香港科技大学(广州)人工智能方向);Tencent AI Lab(腾讯人工智能实验室);Department of Computer Science and Engineering, HKUST(香港科技大学计算机科学与工程系);Guangzhou HKUST Fok Ying Tung Research Institute(广州香港科技大学霍英东研究院)
Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding
University of Science and Technology of China(中国科学技术大学);Jarvis Research Center, Tencent YouTu Lab(腾讯优图实验室贾维斯研究中心);Peking University(北京大学);Westlake University(西湖大学);City University of Hong Kong(香港城市大学)
SSL-SSAW: Self-Supervised Learning with Sigmoid Self-Attention Weighting for Question-Based Sign Language Translation
School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University(计算机科学与技术学院,智能计算学院,天津大学);School of Computer Science and Technology, Tiangong University(计算机科学与技术学院,天津工大大学)
CREST: A Joint Framework for Rationalization and Counterfactual Text Generation
Instituto de Telecomunicações(电信研究所);Instituto Superior Técnico(里斯本高等理工学院);LUMLIS (Lisbon ELLIS Unit)(LUMLIS(里斯本ELLIS单元));Massachusetts Institute of Technology(麻省理工学院);Unbabel(Unbabel公司)
SeLaR: Selective Latent Reasoning in Large Language Models
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology(广东省超高清沉浸式媒体技术重点实验室);Shenzhen Graduate School, Peking University(北京大学深圳研究生院)
CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models
Department of Informatics, Universität Hamburg(汉堡大学信息学院);The University of Sydney(悉尼大学);Alibaba International Digital Commerce(阿里巴巴国际数字商业);Institute of Psychology, Chinese Academy of Sciences(中国科学院心理研究所)
Shapley Value-based Contrastive Alignment for Multimodal Information Extraction
State Key Laboratory of Multimedia Information Processing(多媒体信息处理国家重点实验室);School of Computer Science(计算机学院);Peking University(北京大学);Wangxuan Institute of Computer Technology(王选计算机技术研究所)
Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU
Aalborg University(奥尔堡大学);University of Barcelona(巴塞罗那大学);Computer Vision Center(计算机视觉中心);Milestone Systems(里程碑系统公司);Pioneer Center for Artificial Intelligence(先锋人工智能中心)
Selective Preference Optimization via Token-Level Reward Function Estimation
National Centre for Text Mining, The University of Manchester(曼彻斯特大学文本挖掘中心);School of Artificial Intelligence, Wuhan University(武汉大学人工智能学院);Center for Language and Information Research, Wuhan University(武汉大学语言与信息研究中心);The Fin AI(Fin AI公司);Baidu Inc.(百度公司);Archimedes Research(阿基米德研究)