Cover Image

MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Fengwei, Song, Jiafei, Li, Wenjin Jason, Xue, Gengjian, Zhao, Zhikang, Lu, Yichao, Na, Bailin
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling
by: Song, Jiafei, et al.
Published: (2026)

Long-Term Outlier Prediction Through Outlier Score Modeling
by: Aoki, Yuma, et al.
Published: (2026)

ParallelComp: Parallel Long-Context Compressor for Length Extrapolation
by: Xiong, Jing, et al.
Published: (2025)

Robust Statistical Scaling of Outlier Scores: Improving the Quality of Outlier Probabilities for Outliers (Extended Version)
by: Röchner, Philipp, et al.
Published: (2024)

Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios
by: Tang, Jiwei, et al.
Published: (2024)

OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data
by: Zhao, Yan, et al.
Published: (2026)

SPLA: Block Sparse Plus Linear Attention for Long Context Modeling
by: Wang, Bailin, et al.
Published: (2026)

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
by: Attali, Hugo, et al.
Published: (2024)

Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature
by: Fesser, Lukas, et al.
Published: (2023)

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
by: Attali, Hugo, et al.
Published: (2026)

S$^3$Attention: Improving Long Sequence Attention with Smoothed Skeleton Sketching
by: Wang, Xue, et al.
Published: (2024)

Shielded but Lightweight: Building Practical Confidential Containers with ARM CCA
by: Song, Liantao, et al.
Published: (2026)

EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization
by: Hodo, Benjamin, et al.
Published: (2025)

Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors
by: Wang, Xiangchen, et al.
Published: (2025)

Small Vision-Language Models are Smart Compressors for Long Video Understanding
by: Fei, Junjie, et al.
Published: (2026)

The Global Sections of Chiral de Rham Complexes on Closed Complex Curves
by: Song, Bailin, et al.
Published: (2025)

Simple Vertex Algebras Arising From Congruence Subgroups
by: Dai, Xuanzhong, et al.
Published: (2022)

The global sections of chiral de Rham complexes on closed complex curves
by: Bailin Song, et al.
Published: (2026)

Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning
by: Gai, Jingchu, et al.
Published: (2025)

Efficient Generation of Hidden Outliers for Improved Outlier Detection
by: Cribeiro-Ramallo, Jose, et al.
Published: (2024)

Extended Histogram-based Outlier Score (EHBOS)
by: Islam, Tanvir
Published: (2025)

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor
by: Ma, Guoxin, et al.
Published: (2026)

MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention Distillation
by: Ding, Yidong, et al.
Published: (2025)

Mitigating Artifacts in Pre-quantization Based Scientific Data Compressors with Quantization-aware Interpolation
by: Jiao, Pu, et al.
Published: (2026)

OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model
by: Chen, Liuhan, et al.
Published: (2024)

Bridging Smoothness and Approximation: Theoretical Insights into Over-Smoothing in Graph Neural Networks
by: Yang, Guangrui, et al.
Published: (2024)

Oblique-MERF: Revisiting and Improving MERF for Oblique Photography
by: Zeng, Xiaoyi, et al.
Published: (2024)

In-Context Language Learning: Architectures and Algorithms
by: Akyürek, Ekin, et al.
Published: (2024)

ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigation
by: Sun, Siqi, et al.
Published: (2026)

Large Language Model as Token Compressor and Decompressor
by: Li, Wenbing, et al.
Published: (2026)

Standard monomials and invariant theory of arc spaces II: Symplectic group
by: Linshaw, Andrew R., et al.
Published: (2021)

Standard monomials and invariant theory for arc spaces III: special linear group
by: Linshaw, Andrew R., et al.
Published: (2021)

Standard monomials and invariant theory for arc spaces I: general linear group
by: Linshaw, Andrew R., et al.
Published: (2021)

Commentary on ‘Rationalising Hepatocellular Carcinoma Screening in Chronic Hepatitis B: Evaluation of Predictive Scores in an Australian Cohort’
by: Jiawei Hu, et al.
Published: (2025)

MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization
by: Wang, Zongwu, et al.
Published: (2025)

Can Mamba Learn In Context with Outliers? A Theoretical Generalization Analysis
by: Li, Hongkang, et al.
Published: (2025)

Utilizing Load Shifting for Optimal Compressor Sequencing in Industrial Refrigeration
by: Konda, Rohit, et al.
Published: (2024)

PANICL: Mitigating Over-Reliance on Single Prompt in Visual In-Context Learning
by: Zhang, Jiahao, et al.
Published: (2025)

Changes in Academic Library Space: A Case Study at the University of New South Wales
by: Bailin, Kylie
Published: (2011)

Analysis of the Synergistic Effect of Water Vapor, Thermodynamics, and Dynamics of the Heavy Rainfall Over Henan Province, China in July 2021
by: Yang Yu, et al.
Published: (2025)