:: Library Catalog

Image de couverture de livre

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Danni, Niehues, Jan
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	https://arxiv.org/abs/2510.19546
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

How Transferable are Attribute Controllers on Pretrained Multilingual Translation Models?
par: Liu, Danni, et autres
Publié: (2023)

Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach
par: Li, Siqi, et autres
Publié: (2024)

Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
par: Liu, Danni, et autres
Publié: (2025)

Language-Independent Representations Improve Zero-Shot Summarization
par: Solovyev, Vladimir, et autres
Publié: (2024)

OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion
par: Koneru, Sai, et autres
Publié: (2025)

How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations
par: Lee, Hyunji, et autres
Publié: (2024)

Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024
par: Koneru, Sai, et autres
Publié: (2024)

Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models
par: Ahuja, Sanchit, et autres
Publié: (2026)

KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization
par: Li, Zhaolin, et autres
Publié: (2025)

Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
par: Watts, Ishaan, et autres
Publié: (2026)

Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing
par: Koneru, Sai, et autres
Publié: (2023)

When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR
par: Züfle, Maike, et autres
Publié: (2026)

Mitigating Catastrophic Forgetting in Continual Learning through Model Growth
par: Süalp, Ege, et autres
Publié: (2025)

Evolutionary Strategies lead to Catastrophic Forgetting in LLMs
par: Abdi, Immanuel, et autres
Publié: (2026)

Revisiting Catastrophic Forgetting in Large Language Model Tuning
par: Li, Hongyu, et autres
Publié: (2024)

Contrastive Learning for Task-Independent SpeechLLM-Pretraining
par: Züfle, Maike, et autres
Publié: (2024)

Early-Exit and Instant Confidence Translation Quality Estimation
par: Zouhar, Vilém, et autres
Publié: (2025)

More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs
par: Liu, Chengyuan, et autres
Publié: (2024)

Catastrophic Forgetting in LLMs: A Comparative Analysis Across Language Tasks
par: Haque, Naimul
Publié: (2025)

Do Slides Help? Multi-modal Context for Automatic Transcription of Conference Talks
par: Sinhamahapatra, Supriti, et autres
Publié: (2025)

In-context Language Learning for Endangered Languages in Speech Recognition
par: Li, Zhaolin, et autres
Publié: (2025)

Multimodal In-context Learning for ASR of Low-resource Languages
par: Li, Zhaolin, et autres
Publié: (2026)

Understanding Catastrophic Forgetting in Language Models via Implicit Inference
par: Kotha, Suhas, et autres
Publié: (2023)

Model Editing at Scale leads to Gradual and Catastrophic Forgetting
par: Gupta, Akshat, et autres
Publié: (2024)

Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning
par: Ren, Weijieying, et autres
Publié: (2024)

Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
par: Zhu, Didi, et autres
Publié: (2024)

MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
par: Papi, Sara, et autres
Publié: (2025)

End-to-End Evaluation for Low-Latency Simultaneous Speech Translation
par: Huber, Christian, et autres
Publié: (2023)

Mitigating Catastrophic Forgetting in Mathematical Reasoning Finetuning through Mixed Training
par: Reynolds, John Graham
Publié: (2025)

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
par: Huang, Jianheng, et autres
Publié: (2024)

Intelligent Learning Rate Distribution to reduce Catastrophic Forgetting in Transformers
par: Kenneweg, Philip, et autres
Publié: (2024)

Talk2Ref: A Dataset for Reference Prediction from Scientific Talks
par: Broy, Frederik, et autres
Publié: (2025)

Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs
par: Yu, Zeping, et autres
Publié: (2025)

An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
par: Luo, Yun, et autres
Publié: (2023)

BOOM: Beyond Only One Modality KIT's Multimodal Multilingual Lecture Companion
par: Koneru, Sai, et autres
Publié: (2025)

KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025
par: Koneru, Sai, et autres
Publié: (2025)

Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability
par: Dinh, Tu Anh, et autres
Publié: (2025)

Sigmoid Head for Quality Estimation under Language Ambiguity
par: Dinh, Tu Anh, et autres
Publié: (2026)

Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting
par: Ding, Fei, et autres
Publié: (2025)

Can Similarity-Based Domain-Ordering Reduce Catastrophic Forgetting for Intent Recognition?
par: Mannekote, Amogh, et autres
Publié: (2024)