Copertina

Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yao, Yuxuan, Sheng, Haonan, Lv, Qingsong, Wu, Han, Liu, Shuqi, Liu, Zehua, Liu, Zengyan, Gao, Jiahui, Tan, Haochen, Fu, Xiaojin, Bai, Haoli, So, Hing Cheung, Guo, Zhijiang, Song, Linqi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Activation-Guided Consensus Merging for Large Language Models
di: Yao, Yuxuan, et al.
Pubblicazione: (2025)

1bit-Merging: Dynamic Quantized Merging for Large Language Models
di: Liu, Shuqi, et al.
Pubblicazione: (2025)

Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging
di: Wu, Han, et al.
Pubblicazione: (2025)

Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models
di: Liu, Shuqi, et al.
Pubblicazione: (2025)

Meta-Learning-Based Delayless Subband Adaptive Filter using Complex Self-Attention for Active Noise Control
di: Feng, Pengxing, et al.
Pubblicazione: (2024)

Learning From Correctness Without Prompting Makes LLM Efficient Reasoner
di: Yao, Yuxuan, et al.
Pubblicazione: (2024)

Beyond One-Size-Fits-All Pruning via Evolutionary Metric Search for Large Language Models
di: Liu, Shuqi, et al.
Pubblicazione: (2025)

Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
di: You, Haochen, et al.
Pubblicazione: (2025)

Bi-Chainer: Automated Large Language Models Reasoning with Bidirectional Chaining
di: Liu, Shuqi, et al.
Pubblicazione: (2024)

REG: A Regularization Optimizer for Robust Training Dynamics
di: Liu, Zehua, et al.
Pubblicazione: (2025)

Low-Rank and Row-Sparse Decomposition for Joint DOA Estimation and Distorted Sensor Detection
di: Huang, Huiping, et al.
Pubblicazione: (2022)

Sparse array design for MIMO radar in multipath scenarios
di: Li, Xuchen, et al.
Pubblicazione: (2024)

Robust time-of-arrival localization via ADMM
di: Xiong, Wenxin, et al.
Pubblicazione: (2023)

Rotatable Antenna Aided Mixed Near-Field and Far-Field Communications in the Upper Mid-Band: Interference Analysis and Joint Optimization
di: Zhang, Yunpu, et al.
Pubblicazione: (2025)

Target Localization with Coprime Multistatic MIMO Radar via Coupled Canonical Polyadic Decomposition Based on Joint Eigenvalue Decomposition
di: Liao, Guo-Zhao, et al.
Pubblicazione: (2025)

Target Localization with a Coprime Multistatic MIMO Radar via Coupled Canonical Polyadic Decomposition Based on Joint EVD
di: Liao, Guo-Zhao, et al.
Pubblicazione: (2025)

LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging
di: Liu, Zehua, et al.
Pubblicazione: (2025)

AROMA: Autonomous Rank-one Matrix Adaptation
di: Sheng, Hao Nan, et al.
Pubblicazione: (2025)

Convergence Analysis of Consensus-ADMM for General QCQP
di: Huang, Huiping, et al.
Pubblicazione: (2022)

RIFT: Repurposing Negative Samples via Reward-Informed Fine-Tuning
di: Liu, Zehua, et al.
Pubblicazione: (2026)

Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling
di: Yao, Yuxuan, et al.
Pubblicazione: (2024)

Technology, life‐long learning, and heutagogy
di: Hing‐yu So
Pubblicazione: (2024)

Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models
di: Liu, Shuqi, et al.
Pubblicazione: (2025)

Rotatable Antenna Enabled Multi-Cell Mixed Near-Field and Far-Field Communications
di: Zhang, Yunpu, et al.
Pubblicazione: (2026)

Sparse Fluid Antenna Arrays: Continuous Position Design Beyond Classical DOF Limits
di: Wu, Tuo, et al.
Pubblicazione: (2026)

WeightedKV: Attention Scores Weighted Key-Value Cache Merging for Large Language Models
di: Yuan, Jian, et al.
Pubblicazione: (2025)

MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric
di: Lin, Haokun, et al.
Pubblicazione: (2024)

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
di: Li, Siyuan, et al.
Pubblicazione: (2025)

PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models
di: Tan, Haochen, et al.
Pubblicazione: (2024)

Representations of 3D Rotations: Mathematical Foundations and Comparative Analysis
di: Aiersilan, Aizierjiang, et al.
Pubblicazione: (2025)

A characterization of compactness via bilinear $T1$ theorem
di: Cao, Mingming, et al.
Pubblicazione: (2024)

Limited range extrapolation with quantitative bounds and applications
di: Cao, Mingming, et al.
Pubblicazione: (2022)

Beyond Information: Mechanisms of Risk Communication on Self‐Protective Behavior in Public Health Emergencies
di: Yunpeng Xu, et al.
Pubblicazione: (2026)

Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach
di: Liu, Shuqi, et al.
Pubblicazione: (2025)

FaStfact: Faster, Stronger Long-Form Factuality Evaluations in LLMs
di: Wan, Yingjia, et al.
Pubblicazione: (2025)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
di: Zhang, Luyuan, et al.
Pubblicazione: (2026)

Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
di: Liu, Qingxiang, et al.
Pubblicazione: (2024)

Topology-Aware Integrated Communication, Sensing, and Power Transfer for SAGIN
di: Yu, Han, et al.
Pubblicazione: (2026)

Hybrid Data-Driven SSM for Interpretable and Label-Free mmWave Channel Prediction
di: Sun, Yiyong, et al.
Pubblicazione: (2024)

Performance Analysis and Low-Complexity Beamforming Design for Near-Field Physical Layer Security
di: Zhang, Yunpu, et al.
Pubblicazione: (2024)