Accelerating Transformers with Spectrum-Preserving Token Merging
Fuente:
arXiv
Saved in:
| Main Authors: | Tran, Hoai-Chau, Nguyen, Duy M. H., Nguyen, Duy M., Nguyen, Trung-Tin, Le, Ngan, Xie, Pengtao, Sonntag, Daniel, Zou, James Y., Nguyen, Binh T., Niepert, Mathias |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
by: Nguyen, Duy M. H., et al.
Published: (2026)
by: Nguyen, Duy M. H., et al.
Published: (2026)
ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
by: Nguyen, Duy M. H., et al.
Published: (2024)
by: Nguyen, Duy M. H., et al.
Published: (2024)
Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model
by: Nguyen, Duy M. H., et al.
Published: (2024)
by: Nguyen, Duy M. H., et al.
Published: (2024)
Modifications of the BIC for order selection in finite mixture models
by: Nguyen, Hien Duy, et al.
Published: (2025)
by: Nguyen, Hien Duy, et al.
Published: (2025)
On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation
by: Diep, Nghiem T., et al.
Published: (2025)
by: Diep, Nghiem T., et al.
Published: (2025)
Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
by: Nguyen, Duy M. H., et al.
Published: (2024)
by: Nguyen, Duy M. H., et al.
Published: (2024)
SparseSAM: Structured Sparsification of Activations in Segment Anything Models
by: Tran, Hoai-Chau, et al.
Published: (2026)
by: Tran, Hoai-Chau, et al.
Published: (2026)
How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?
by: Tran, Tuan Anh, et al.
Published: (2025)
by: Tran, Tuan Anh, et al.
Published: (2025)
EFL teachers’ perceptions of professional development activities and their effects in a non-anglosphere context
by: Duy Binh Nguyen
Published: (2022)
by: Duy Binh Nguyen
Published: (2022)
Reinforcing Trustworthiness in Multimodal Emotional Support Systems
by: Le, Huy M., et al.
Published: (2025)
by: Le, Huy M., et al.
Published: (2025)
SVM On Trees
by: Tran, Cong-Huan, et al.
Published: (2026)
by: Tran, Cong-Huan, et al.
Published: (2026)
Risk Bounds for Mixture Density Estimation on Compact Domains via the $h$-Lifted Kullback--Leibler Divergence
by: Chong, Mark Chiu, et al.
Published: (2024)
by: Chong, Mark Chiu, et al.
Published: (2024)
Bridging the divide between technology and pedagogy: What does a bibliometric analysis reveal about the future of inducing flow in e‐learning?
by: Nguyen Binh Phuong Duy
Published: (2026)
by: Nguyen Binh Phuong Duy
Published: (2026)
Revisiting Incremental Stochastic Majorization-Minimization Algorithms with Applications to Mixture of Experts
by: Tran, TrungKhang, et al.
Published: (2026)
by: Tran, TrungKhang, et al.
Published: (2026)
Fake Advertisements Detection Using Automated Multimodal Learning: A Case Study for Vietnamese Real Estate Data
by: Nguyen, Duy, et al.
Published: (2025)
by: Nguyen, Duy, et al.
Published: (2025)
Distributional Surgery for Language Model Activations
by: Nguyen, Bao, et al.
Published: (2025)
by: Nguyen, Bao, et al.
Published: (2025)
Continuous-time optimal investment with portfolio constraints: a reinforcement learning approach
by: Chau, Huy, et al.
Published: (2024)
by: Chau, Huy, et al.
Published: (2024)
On the large-sample limits of some Bayesian model evaluation statistics
by: Nguyen, Hien Duy, et al.
Published: (2025)
by: Nguyen, Hien Duy, et al.
Published: (2025)
Approximation rates for finite mixtures of location-scale models and fast least-squares estimators
by: Nguyen, Hien Duy, et al.
Published: (2025)
by: Nguyen, Hien Duy, et al.
Published: (2025)
CAMEx: Curvature-aware Merging of Experts
by: Nguyen, Dung V., et al.
Published: (2025)
by: Nguyen, Dung V., et al.
Published: (2025)
The Impact of Transformational Leadership on Enterprise Digital Transformation Effectiveness: The Mediating Role of Employees' Digital Skills
by: Chuc, Nguyen Duy
Published: (2025)
by: Chuc, Nguyen Duy
Published: (2025)
Wind Speed Probability Distribution Based on Adaptive Bandwidth Kernel Density Estimation Model for Wind Farm Application
by: Tin Trung Chau, et al.
Published: (2025)
by: Tin Trung Chau, et al.
Published: (2025)
On short-time behavior of implied volatility in a market model with indexes
by: Chau, Huy N., et al.
Published: (2024)
by: Chau, Huy N., et al.
Published: (2024)
TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
by: Nguyen, Truong, et al.
Published: (2026)
by: Nguyen, Truong, et al.
Published: (2026)
A Comprehensive Digital Workflow for the Treatment of Excessive Gingival Display Caused by Altered Passive Eruption: A Prospective Case Series
by: Nguyen Trong Tinh, et al.
Published: (2026)
by: Nguyen Trong Tinh, et al.
Published: (2026)
ARtVista: Gateway To Empower Anyone Into Artist
by: Hoang, Trong-Vu, et al.
Published: (2024)
by: Hoang, Trong-Vu, et al.
Published: (2024)
VirDA: Reusing Backbone for Unsupervised Domain Adaptation with Visual Reprogramming
by: Nguyen, Duy, et al.
Published: (2025)
by: Nguyen, Duy, et al.
Published: (2025)
Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling
by: Nguyen, Phuc Minh, et al.
Published: (2025)
by: Nguyen, Phuc Minh, et al.
Published: (2025)
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
by: Do, Minh-Thu, et al.
Published: (2026)
by: Do, Minh-Thu, et al.
Published: (2026)
Cold-start Recommendation by Personalized Embedding Region Elicitation
by: Nguyen, Hieu Trung, et al.
Published: (2024)
by: Nguyen, Hieu Trung, et al.
Published: (2024)
SegMaFormer: A Hybrid State-Space and Transformer Model for Efficient Segmentation
by: Nguyen, Duy D., et al.
Published: (2026)
by: Nguyen, Duy D., et al.
Published: (2026)
Molecular Characterization and Genetic Diversity of Isolated Foot‐and‐Mouth Disease Viruses Circulating in Cattle in The Mekong Delta Provinces, Vietnam
by: Nguyen Phuc Khanh, et al.
Published: (2025)
by: Nguyen Phuc Khanh, et al.
Published: (2025)
S-Chain: Structured Visual Chain-of-Thought For Medicine
by: Le-Duc, Khai, et al.
Published: (2025)
by: Le-Duc, Khai, et al.
Published: (2025)
Expert Merging in Sparse Mixture of Experts with Nash Bargaining
by: Nguyen, Dung V., et al.
Published: (2025)
by: Nguyen, Dung V., et al.
Published: (2025)
CTPD: Cross Tokenizer Preference Distillation
by: Nguyen, Truong, et al.
Published: (2026)
by: Nguyen, Truong, et al.
Published: (2026)
High-dimensional Many-to-many-to-many Mediation Analysis
by: Nguyen, Tien Dat, et al.
Published: (2026)
by: Nguyen, Tien Dat, et al.
Published: (2026)
Further achievements on the chemical composition and bioactivities of Euphorbia tithymaloides
by: Nguyen Vu Duy Khang, et al.
Published: (2025)
by: Nguyen Vu Duy Khang, et al.
Published: (2025)
WriteViT: Handwritten Text Generation with Vision Transformer
by: Nam, Dang Hoai, et al.
Published: (2025)
by: Nam, Dang Hoai, et al.
Published: (2025)
Deep Learning for Ophthalmology: The State-of-the-Art and Future Trends
by: Nguyen, Duy M. H., et al.
Published: (2025)
by: Nguyen, Duy M. H., et al.
Published: (2025)
Supercharacters of finite abelian groups and applications to spectra of $U$-unitary Cayley graphs
by: Nguyen, Tung T., et al.
Published: (2025)
by: Nguyen, Tung T., et al.
Published: (2025)
Similar Items
-
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
by: Nguyen, Duy M. H., et al.
Published: (2026) -
ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
by: Nguyen, Duy M. H., et al.
Published: (2024) -
Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model
by: Nguyen, Duy M. H., et al.
Published: (2024) -
Modifications of the BIC for order selection in finite mixture models
by: Nguyen, Hien Duy, et al.
Published: (2025) -
On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation
by: Diep, Nghiem T., et al.
Published: (2025)