Imagen de Portada

Efficient Multi-Task Inferencing: Model Merging with Gromov-Wasserstein Feature Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fang, Luyang, Latif, Ehsan, Lu, Haoran, Zhou, Yifan, Ma, Ping, Zhai, Xiaoming
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Efficient Multi-Task Inferencing with a Shared Backbone and Lightweight Task-Specific Adapters for Automatic Scoring
por: Latif, Ehsan, et al.
Publicado: (2024)

Knowledge Distillation of LLM for Automatic Scoring of Science Education Assessments
por: Latif, Ehsan, et al.
Publicado: (2023)

Using Generative AI and Multi-Agents to Provide Automatic Feedback
por: Guo, Shuchen, et al.
Publicado: (2024)

G-SciEdBERT: A Contextualized LLM for Science Assessment Tasks in German
por: Latif, Ehsan, et al.
Publicado: (2024)

Fine-tuning ChatGPT for Automatic Scoring of Written Scientific Explanations in Chinese
por: Yang, Jie, et al.
Publicado: (2025)

Using GPT-4 to Augment Unbalanced Data for Automatic Scoring
por: Fang, Luyang, et al.
Publicado: (2023)

Gemini Pro Defeated by GPT-4V: Evidence from Education
por: Lee, Gyeong-Geon, et al.
Publicado: (2023)

Applying Large Language Models and Chain-of-Thought for Automatic Scoring
por: Lee, Gyeong-Geon, et al.
Publicado: (2023)

InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
por: Wang, Yuanyi, et al.
Publicado: (2025)

Generalizable and Efficient Automated Scoring with a Knowledge-Distilled Multi-Task Mixture-of-Experts
por: Fang, Luyang, et al.
Publicado: (2025)

Unveiling Scoring Processes: Dissecting the Differences between LLMs and Human Graders in Automatic Scoring
por: Wu, Xuansheng, et al.
Publicado: (2024)

SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches
por: Latif, Ehsan, et al.
Publicado: (2025)

Advancing Education through Tutoring Systems: A Systematic Literature Review
por: Liu, Vincent, et al.
Publicado: (2025)

AI Gender Bias, Disparities, and Fairness: Does Training Data Matter?
por: Latif, Ehsan, et al.
Publicado: (2023)

Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions
por: Fang, Luyang, et al.
Publicado: (2025)

Privacy-Preserved Automated Scoring using Federated Learning for Educational Research
por: Latif, Ehsan, et al.
Publicado: (2025)

Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment
por: Lu, Keming, et al.
Publicado: (2024)

MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic
por: Zhou, Yuyan, et al.
Publicado: (2024)

Human-Centered Design for AI-based Automatically Generated Assessment Reports: A Systematic Review
por: Latif, Ehsan, et al.
Publicado: (2024)

Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning
por: Aakanksha, et al.
Publicado: (2024)

Multi-Task Model Merging via Adaptive Weight Disentanglement
por: Xiong, Feng, et al.
Publicado: (2024)

Min Generalized Sliced Gromov Wasserstein: A Scalable Path to Gromov Wasserstein
por: Shahbazi, Ashkan, et al.
Publicado: (2026)

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
por: He, Yifei, et al.
Publicado: (2024)

AM$^3$Safety: Towards Data Efficient Alignment of Multi-modal Multi-turn Safety for MLLMs
por: Zhu, Han, et al.
Publicado: (2026)

Multi-objective Evolutionary Merging Enables Efficient Reasoning Models
por: Iacobelli, Mario, et al.
Publicado: (2026)

Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks
por: Wang, Zheng, et al.
Publicado: (2024)

FlowMM: Cross-Modal Information Flow Guided KV Cache Merging for Efficient Multimodal Context Inference
por: Li, Kunxi, et al.
Publicado: (2025)

Merging by Matching Models in Task Parameter Subspaces
por: Tam, Derek, et al.
Publicado: (2023)

Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
por: Morrison, Jacob, et al.
Publicado: (2024)

Artificial Intelligence Bias on English Language Learners in Automatic Scoring
por: Guo, Shuchen, et al.
Publicado: (2025)

DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models
por: Chen, Ruizhe, et al.
Publicado: (2025)

Train It and Forget It: Merge Lists are Unnecessary for BPE Inference in Language Models
por: Sawada, Tomohiro, et al.
Publicado: (2025)

MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs
por: Zhou, Yuhang, et al.
Publicado: (2025)

Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models
por: Wang, Shuo, et al.
Publicado: (2024)

A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment
por: Corbeil, Jean-Philippe, et al.
Publicado: (2025)

Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization
por: Lin, Tzu-Quan, et al.
Publicado: (2025)

GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
por: Tang, Jiwei, et al.
Publicado: (2025)

Efficient Knowledge Transfer in Multi-Task Learning through Task-Adaptive Low-Rank Representation
por: Zhang, Xiao, et al.
Publicado: (2025)

Fused Gromov-Wasserstein Distance with Feature Selection
por: Lee, Harlin, et al.
Publicado: (2026)

Reasoning Pattern Alignment Merging for Adaptive Reasoning
por: Zhong, Zhaofeng, et al.
Publicado: (2026)