Imagen de Portada

From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cui, Chaoqun, Wang, Shijing, Huang, Liangbin, Gu, Qingqing, Huang, Zhaolong, Zeng, Xiao, Mao, Wenji
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling
por: Cui, Chaoqun, et al.
Publicado: (2026)

Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization
por: Cui, Chaoqun, et al.
Publicado: (2025)

CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization
por: Huang, Liangbin, et al.
Publicado: (2026)

Agentic Reward Modeling: Verifying GUI Agent via Online Proactive Interaction
por: Cui, Chaoqun, et al.
Publicado: (2026)

Let Storytelling Tell Vivid Stories: An Expressive and Fluent Multimodal Storyteller
por: Zang, Chuanqi, et al.
Publicado: (2024)

A Universal Harmonic Discriminator for High-quality GAN-based Vocoder
por: Xu, Nan, et al.
Publicado: (2025)

AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates
por: Chen, Shaolong, et al.
Publicado: (2026)

VL4Gaze: Unleashing Vision-Language Models for Gaze Following
por: Wang, Shijing, et al.
Publicado: (2025)

Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings
por: Liu, Xuanqing, et al.
Publicado: (2025)

Visible Light‐Induced Single‐Atom Insertion of Indenes via Aerobic Ring Scission–Condensation–Rearomatization
por: Guohui Zeng, et al.
Publicado: (2025)

Adaptive Social Learning via Mode Policy Optimization for Language Agents
por: Wang, Minzheng, et al.
Publicado: (2025)

Hacked in Translation -- from Subtitles to Complete Takeover
por: Herscovici, Omri, et al.
Publicado: (2024)

Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
por: Chen, Kun, et al.
Publicado: (2025)

VividListener: Expressive and Controllable Listener Dynamics Modeling for Multi-Modal Responsive Interaction
por: Li, Shiying, et al.
Publicado: (2025)

From Speech to Subtitles: Evaluating ASR Models in Subtitling Italian Television Programs
por: Lucca, Alessandro, et al.
Publicado: (2025)

From Emotional Utterances to Institutional Norms: Translational Authority and the Formation of Organizational Ethics
por: Kimura, Hinano
Publicado: (2026)

Pivot Templators’ Challenges and Training: Insights from a Survey Study with Subtitlers and Subtitler Trainers
por: Hanna Pięta
Publicado: (2023)

VTS-LLM: Domain-Adaptive LLM Agent for Enhancing Awareness in Vessel Traffic Services through Natural Language
por: Sun, Sijin, et al.
Publicado: (2025)

Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following
por: Wang, Shijing, et al.
Publicado: (2026)

Towards Visually-Guided Movie Subtitle Translation for Indic Languages
por: Chintada, Tarun, et al.
Publicado: (2026)

Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection
por: Cui, Chaoqun, et al.
Publicado: (2025)

LLM-Driven Preference Data Synthesis for Proactive Prediction of the Next User Utterance in Human-Machine Dialogue
por: Wang, Jinqiang, et al.
Publicado: (2025)

Suppressing Uncertainty in Gaze Estimation
por: Wang, Shijing, et al.
Publicado: (2024)

The Adaptive Trajectory of the Normal Force Vector in the Polishing of Curved Surface Component Robots
por: Jiale Xu, et al.
Publicado: (2025)

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion
por: Zeng, Yu, et al.
Publicado: (2024)

SilhouetteTell: Practical Video Identification Leveraging Blurred Recordings of Video Subtitles
por: Huang, Guanchong, et al.
Publicado: (2025)

Transition‐Metal‐Free Alkynylthiolation of Tertiary α‐ Carbonyl Bromides
por: Donghui Xing, et al.
Publicado: (2025)

MSGCoOp: Multiple Semantic-Guided Context Optimization for Few-Shot Learning
por: Wang, Zhaolong, et al.
Publicado: (2025)

A Case Study on Contextual Machine Translation in a Professional Scenario of Subtitling
por: Vincent, Sebastian, et al.
Publicado: (2024)

Is Transcreation Another Way of Translating? Subtitling Estrella Damm’s Advertising Campaigns into English
por: Montse Corrius
Publicado: (2023)

LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues
por: Stacey, Joe, et al.
Publicado: (2024)

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
por: Xu, Haoran, et al.
Publicado: (2024)

Leveraging Broadcast Media Subtitle Transcripts for Automatic Speech Recognition and Subtitling
por: Poncelet, Jakob, et al.
Publicado: (2025)

PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement
por: Hu, Teng, et al.
Publicado: (2025)

CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation
por: Cui, Guofeng, et al.
Publicado: (2025)

Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences
por: Hasan, Mohammad Saqib, et al.
Publicado: (2025)

Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation
por: Cao, Zhiyu, et al.
Publicado: (2025)

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization
por: Huang, Yixu, et al.
Publicado: (2026)

Vivid: Journal of Language and Literature
Publicado: (2024)

From Randomized Response to Randomized Index: Answering Subset Counting Queries with Local Differential Privacy
por: Ye, Qingqing, et al.
Publicado: (2025)