Imagen de Portada

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wu, Wei, Chen, Liyi, Xiao, Congxi, Wang, Tianfu, Wang, Qimeng, Lu, Chengqiang, Gao, Yan, Wu, Yi, Hu, Yao, Xiong, Hui
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Aligning Large Language Models with Searcher Preferences
por: Wu, Wei, et al.
Publicado: (2026)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
por: Wu, Wei, et al.
Publicado: (2024)

Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
por: Yang, Dongjie, et al.
Publicado: (2025)

RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
por: Zhang, Rongyang, et al.
Publicado: (2025)

RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios
por: Zhao, Fei, et al.
Publicado: (2025)

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
por: Huang, Yuqing, et al.
Publicado: (2025)

TimeFound: A Foundation Model for Time Series Forecasting
por: Xiao, Congxi, et al.
Publicado: (2025)

Identifiable Representation and Model Learning for Latent Dynamic Systems
por: Zhang, Congxi, et al.
Publicado: (2024)

MoDification: Mixture of Depths Made Easy
por: Zhang, Chen, et al.
Publicado: (2024)

Explaining Length Bias in LLM-Based Preference Evaluations
por: Hu, Zhengyu, et al.
Publicado: (2024)

Benchmarking Large Language Models for Conversational Question Answering in Multi-instructional Documents
por: Wu, Shiwei, et al.
Publicado: (2024)

FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning
por: Luo, Haozheng, et al.
Publicado: (2026)

Efficient Pretraining Length Scaling
por: Wu, Bohong, et al.
Publicado: (2025)

Tracking control of latent dynamic systems with application to spacecraft attitude control
por: Zhang, Congxi, et al.
Publicado: (2024)

EntroCut: Entropy-Guided Adaptive Truncation for Efficient Chain-of-Thought Reasoning in Small-scale Large Reasoning Models
por: Yan, Hongxi, et al.
Publicado: (2026)

Dual-Student Knowledge Distillation Networks for Unsupervised Anomaly Detection
por: Yao, Liyi, et al.
Publicado: (2024)

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
por: Wei, Songtao, et al.
Publicado: (2026)

Exploring the Early Cardiovascular Dynamics in TOF Fetuses
por: Kui Zhang, et al.
Publicado: (2025)

ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
por: Yi, Jingyang, et al.
Publicado: (2025)

Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty
por: Yu, Zewei, et al.
Publicado: (2026)

An Efficient Outlier Detection Algorithm for Data Streaming
por: Hu, Rui, et al.
Publicado: (2025)

AFDGCF: Adaptive Feature De-correlation Graph Collaborative Filtering for Recommendations
por: Wu, Wei, et al.
Publicado: (2024)

Efficient Preparation of Quantum States via Randomized Truncation
por: Wang, Yue, et al.
Publicado: (2025)

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
por: Wu, Xingyu, et al.
Publicado: (2025)

VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
por: Wu, Shiwei, et al.
Publicado: (2024)

SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning
por: Hu, Chenzhi, et al.
Publicado: (2026)

Adapting to Length Shift: FlexiLength Network for Trajectory Prediction
por: Xu, Yi, et al.
Publicado: (2024)

WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
por: Savadikar, Chinmay, et al.
Publicado: (2023)

Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization
por: Sun, Peilin, et al.
Publicado: (2026)

Outlier-Aware Post-Training Quantization for Image Super-Resolution
por: Wang, Hailing, et al.
Publicado: (2025)

ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstruction
por: Liang, Jie, et al.
Publicado: (2026)

Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation
por: Chen, Wei-Rui, et al.
Publicado: (2025)

Dynamic Sparse Learning: A Novel Paradigm for Efficient Recommendation
por: Wang, Shuyao, et al.
Publicado: (2024)

Mechanistic Insights Into Anti‐Kasha, Persistent, and Self‐Trapped Emission in (C 6 H 16 N 2 ) 2 InCl 7 :Sb 3+ Hybrids for Multi‐Level Anti‐Counterfeiting Application
por: Hu Wang, et al.
Publicado: (2025)

Advancing Testicular Trauma Diagnosis
por: Jingdan Cheng, et al.
Publicado: (2025)

H$^3$GNNs: Harmonizing Heterophily and Homophily in GNNs via Joint Structural Node Encoding and Self-Supervised Learning
por: Xue, Rui, et al.
Publicado: (2025)

Object Pose Estimation via the Aggregation of Diffusion Features
por: Wang, Tianfu, et al.
Publicado: (2024)

Robustness Feature Adapter for Efficient Adversarial Training
por: Wu, Quanwei, et al.
Publicado: (2025)

Vript: A Video Is Worth Thousands of Words
por: Yang, Dongjie, et al.
Publicado: (2024)

Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
por: Hu, Jerry Yao-Chieh, et al.
Publicado: (2024)