Cover Image

Probabilistic Token Alignment for Large Language Model Fusion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zeng, Runjia, Liang, James Chenhao, Han, Cheng, Cao, Zhiwen, Liu, Jiahao, Quan, Xiaojun, Chen, Yingjie Victor, Huang, Lifu, Geng, Tong, Wang, Qifan, Liu, Dongfang
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching
by: Zeng, Runjia, et al.
Published: (2026)

Visual Fourier Prompt Tuning
by: Zeng, Runjia, et al.
Published: (2024)

MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper
by: Zeng, Runjia, et al.
Published: (2025)

Inertial Confinement Fusion Forecasting via Large Language Models
by: Chen, Mingkai, et al.
Published: (2024)

ProMotion: Prototypes As Motion Learners
by: Lu, Yawen, et al.
Published: (2024)

Re-Imagining Multimodal Instruction Tuning: A Representation View
by: Liu, Yiyang, et al.
Published: (2025)

M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning
by: Wang, Taowen, et al.
Published: (2024)

Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?
by: Han, Cheng, et al.
Published: (2024)

Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization
by: Gao, Shiping, et al.
Published: (2026)

Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks
by: Cheng, Zhiyuan, et al.
Published: (2024)

All You Need is One: Capsule Prompt Tuning with a Single Vector
by: Liu, Yiyang, et al.
Published: (2025)

Diff-PIC: Revolutionizing Particle-In-Cell Nuclear Fusion Simulation with Diffusion Models
by: Liu, Chuan, et al.
Published: (2024)

A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning
by: Liu, Changyu, et al.
Published: (2026)

Prototypical Transformer as Unified Motion Learners
by: Han, Cheng, et al.
Published: (2024)

Q-Bridge: Code Translation for Quantum Machine Learning via LLMs
by: Zeng, Runjia, et al.
Published: (2026)

AMD: Automatic Multi-step Distillation of Large-scale Vision Models
by: Han, Cheng, et al.
Published: (2024)

On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning
by: Liu, Changyu, et al.
Published: (2026)

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics
by: Wang, Taowen, et al.
Published: (2024)

Advantage-Guided Distillation for Preference Alignment in Small Language Models
by: Gao, Shiping, et al.
Published: (2025)

EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction
by: Yang, Li, et al.
Published: (2024)

Error-driven Data-efficient Large Multimodal Model Tuning
by: Yao, Barry Menglong, et al.
Published: (2024)

Cool-Fusion: Fuse Large Language Models without Training
by: Liu, Cong, et al.
Published: (2024)

PsyPlay: Personality-Infused Role-Playing Conversational Agents
by: Yang, Tao, et al.
Published: (2025)

TokenBlowUp: Resolving Representational Singularities in LLM Token Spaces via Monoidal Transformations
by: Zhao, Dongfang
Published: (2025)

Fusion is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
by: Cheng, Zhiyuan, et al.
Published: (2023)

Image Translation as Diffusion Visual Programmers
by: Han, Cheng, et al.
Published: (2024)

Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction
by: Xie, Yuanbo, et al.
Published: (2025)

Alirector: Alignment-Enhanced Chinese Grammatical Error Corrector
by: Yang, Haihui, et al.
Published: (2024)

The role of hydroxyl groups in poly(ionic liquid)s on CO2 cycloaddition with epoxides in the view of catalytic kinetics
by: Chenhao Wang, et al.
Published: (2025)

SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving
by: Cui, Yiming, et al.
Published: (2024)

Orthogonal Time Frequency Space with Delay-Doppler Alignment Modulation
by: Liu, Xianda, et al.
Published: (2024)

Knowledge Fusion of Large Language Models
by: Wan, Fanqi, et al.
Published: (2024)

AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
by: Qi, Jingyuan, et al.
Published: (2025)

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
by: Wang, Haibo, et al.
Published: (2024)

How Do Large Language Models Learn Concepts During Continual Pre-Training?
by: Yao, Barry Menglong, et al.
Published: (2026)

Visual Agents as Fast and Slow Thinkers
by: Sun, Guangyan, et al.
Published: (2024)

Approximate Fiber Product: A Preliminary Algebraic-Geometric Perspective on Multimodal Embedding Alignment
by: Zhao, Dongfang
Published: (2024)

CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion
by: Liu, Jinyuan, et al.
Published: (2022)

Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
by: Liu, Hanbing, et al.
Published: (2025)

Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
by: Liu, Quan, et al.
Published: (2024)