Papers Continual Pretraining
“Continual Pretraining” 태그가 달린 논문 149편 · 필터 해제
Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position
The architectural design of Large Language Models (LLMs) is shifting from traditional full-attention-only models to hybrid models, which combine different attention modules to improve long-context efficiency and performa…
Continual PretrainingSpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization
Recently, linear attention layers have been increasingly adopted to replace softmax attention at scale for long-context modeling. However, existing context extension approaches typically apply continued pretraining direc…
Continual PretrainingInformation RetrievalStudying Image Tokenizers as Visual Languages in Unified Multimodal Models
Image tokenizers define the ``visual language'' of unified multimodal models, yet are commonly studied through isolated metrics or generation-/understanding-only evaluations. These evaluations do not fully capture how vi…
Continual PretrainingMetaboLLM: a metabolomics-specialized large language model for biochemical knowledge integration and predictive metabolite graph construction
Metabolomics knowledge is distributed across heterogeneous resources and remains difficult to translate into predictive representations. We developed MetaboLLM, a metabolomics-specialized large language model adapted thr…
Continual PretrainingAXIS: A Growable Community-Driven Data Engine for Scalable Robot Manipulation
Learning effective robot manipulation policies requires diverse, high-quality demonstrations, yet existing data pipelines are often difficult to scale because they rely on specialized hardware, centralized operators, or …
Continual PretrainingRobot ManipulationThe Blessing of Dimensionality: How Near-Orthogonality in High-Dimensional Spaces Explains Temporal Portability
Fine-tuning has been widely used to adapt large language models (LLMs) for domain-specific tasks. Parameter efficient fine-tuning (PEFT) methods such as low-rank adaptation (LoRA) are frequently used to reduce computatio…
Continual PretrainingDiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
Large language models increasingly \emph{understand} dialectal English, yet still \emph{produce} only standard, US-leaning English, leaving dialectal generation, the harder half of the problem, largely unaddressed. We in…
Continual PretrainingLACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods. Unlearning has emerged as a promising solution, with state-of-th…
Continual PretrainingReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP
CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment. As downstream applications increasingly demand visually ground…
Continual PretrainingTrade-offs in Medical LLM Adaptation: An Empirical Study in French QA
The development of large language models (LLMs) has led to an increased focus on their adaptation to specialized domains and languages, yet the effectiveness of domain adaptation strategies remains unclear. We present a …
Continual PretrainingDomain AdaptationTowards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applications
Large language model (LLM)-based multi-agent systems demonstrate strong performance on complex reasoning and task execution, enabling broad enterprise applications. However, production deployment remains challenging due …
Continual PretrainingDomain AdaptationDECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification
Classification tasks require annotated data, which can often be expensive, time-consuming, or even unfeasible to collect. This is the case of the medical domain, where large datasets often have few annotated examples. To…
Continual PretrainingImproving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning
Large language models (LLMs) trained predominantly on English data encode substantial world knowledge, yet often fail to express it reliably in other languages, a phenomenon known as cross-lingual factual inconsistency. …
Reinforcement LearningContinual PretrainingBackdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the…
Continual PretrainingParameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models
While continual pretraining~(CPT) is a practical way to extend large language models to new languages, naïve finetuning on targeted data erodes existing capabilities through catastrophic forgetting. Organizing training a…
Reading ComprehensionContinual PretrainingLanguage AcquisitionGeneral KnowledgeFTibSuite: A Comprehensive Resource Suite for Tibetan Vision-Language Modeling
Vision-language models have progressed rapidly, but Tibetan remains a severely underserved low-resource language due to the lack of reproducible training and evaluation infrastructure. To fill this gap, we introduce FTib…
Continual PretrainingARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning
Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable answers. However, scaling rubric-based RL remains challenging: existin…
Reinforcement LearningContinual PretrainingInstruction FollowingUniversal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining
Computed tomography (CT) is a central to three-dimensional medical imaging, yet CT-based artificial intelligence remains fragmented across task-specific models for segmentation, classification, registration, and report a…
Representation LearningContinual Pretrainingm3BERT: A Modern, Multi-lingual, Matryoshka Bidirectional Encoder
Embedding models are pivotal in industrial information retrieval systems like search and advertising. However, existing pretrained models often exhibit fixed architectures and embedding dimensionalities, posing significa…
Continual PretrainingInformation RetrievalFlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify them in parallel. However, conventional …
Continual Pretraining