Image de couverture de livre

SwitchCIT: Switching for Continual Instruction Tuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Xinbo, Hartman, Max, Jayaraman, Vidhata Arjun, Varshney, Lav R.
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language Models
par: Hartman, Max, et autres
Publié: (2025)

Transformer-based Causal Language Models Perform Clustering
par: Wu, Xinbo, et autres
Publié: (2024)

Hiding in Plain Sight: Detectability-Aware Antidistillation of Reasoning Models
par: Hartman, Max, et autres
Publié: (2026)

A Meta-Learning Perspective on Transformers for Causal Language Modeling
par: Wu, Xinbo, et autres
Publié: (2023)

SparseJEPA: Sparse Representation Learning of Joint Embedding Predictive Architectures
par: Hartman, Max, et autres
Publié: (2025)

Context-Gated Associative Retrieval: From Theory to Transformers
par: Choraria, Moulik, et autres
Publié: (2026)

Beyond Bilingual Transfer: Multilingual Code-Switching in Instruction Tuning
par: Asano, Shunta, et autres
Publié: (2026)

Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations
par: Cherukuri, Kalyan, et autres
Publié: (2026)

Efficient Model-Agnostic Multi-Group Equivariant Networks
par: Baltaji, Razan, et autres
Publié: (2023)

ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responses
par: Zong, Chang, et autres
Publié: (2024)

Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation
par: Baltaji, Razan, et autres
Publié: (2024)

Concealment of Intent: A Game-Theoretic Analysis
par: Wu, Xinbo, et autres
Publié: (2025)

Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning
par: Singhal, Raghav, et autres
Publié: (2025)

Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs
par: Sinha, Aditya, et autres
Publié: (2026)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
par: Zhang, Xiaoyun, et autres
Publié: (2025)

Energy-Aware Routing to Large Reasoning Models
par: Ellis-Mohr, Austin R., et autres
Publié: (2025)

AdaSwitch: Balancing Exploration and Guidance in Knowledge Distillation via Adaptive Switching
par: Peng, Jingyu, et autres
Publié: (2025)

SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset
par: Xie, Peng, et autres
Publié: (2025)

ExpliCIT-QA: Explainable Code-Based Image Table Question Answering
par: Lagos, Maximiliano Hormazábal, et autres
Publié: (2025)

A Theoretical Game of Attacks via Compositional Skills
par: Wu, Xinbo, et autres
Publié: (2026)

Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages
par: Kellert, Olga, et autres
Publié: (2025)

Instruction Tuning With Loss Over Instructions
par: Shi, Zhengyan, et autres
Publié: (2024)

MixReasoning: Switching Modes to Think
par: Lu, Haiquan, et autres
Publié: (2025)

Enhancing Multimodal Continual Instruction Tuning with BranchLoRA
par: Zhang, Duzhen, et autres
Publié: (2025)

Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning
par: Lin, Peiyi, et autres
Publié: (2025)

Computational Approaches to Arabic-English Code-Switching
par: Sabty, Caroline
Publié: (2024)

Indic-TunedLens: Interpreting Multilingual Models in Indian Languages
par: Panchal, Mihir, et autres
Publié: (2026)

Conditioning LLMs to Generate Code-Switched Text
par: Heredia, Maite, et autres
Publié: (2025)

Mind the Gap: Conformative Decoding to Improve Output Diversity of Instruction-Tuned Large Language Models
par: Peeperkorn, Max, et autres
Publié: (2025)

Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs
par: Wu, Xinwei, et autres
Publié: (2026)

Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning
par: He, Yongquan, et autres
Publié: (2024)

MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis
par: Guo, Haiyun, et autres
Publié: (2025)

ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models
par: Liu, Jing, et autres
Publié: (2024)

SwitchLoRA: Switched Low-Rank Adaptation Can Learn Full-Rank Information
par: Zhou, Kaiye, et autres
Publié: (2024)

Detecting Propaganda Techniques in Code-Switched Social Media Text
par: Salman, Muhammad Umar, et autres
Publié: (2023)

Rethinking Table Instruction Tuning
par: Deng, Naihao, et autres
Publié: (2025)

Many LLMs Are More Utilitarian Than One
par: Keshmirian, Anita, et autres
Publié: (2025)

ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings
par: Jeon, Jangyeong, et autres
Publié: (2024)

Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding
par: Yoo, Haneul, et autres
Publié: (2024)

MANTIS: Interleaved Multi-Image Instruction Tuning
par: Jiang, Dongfu, et autres
Publié: (2024)