Copertina

When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Nan, Kwek, Eugene, Zhang, Yusen, Nguyen, Ngoc-Hieu, Mitra, Prasenjit, Zhang, Rui
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals
di: Zhang, Nan, et al.
Pubblicazione: (2026)

TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs
di: Zhang, Yuxiang, et al.
Pubblicazione: (2025)

COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens
di: Kwek, Eugene, et al.
Pubblicazione: (2025)

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training
di: Matsutani, Kohsei, et al.
Pubblicazione: (2026)

Reasoning Planning for Language Models
di: Nguyen, Bao, et al.
Pubblicazione: (2025)

When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
di: Ye, Wen, et al.
Pubblicazione: (2025)

Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning
di: Li, Zhen, et al.
Pubblicazione: (2025)

On the Compressibility of Quantized Large Language Models
di: Mao, Yu, et al.
Pubblicazione: (2024)

A General Benchmark Framework is Dynamic Graph Neural Network Need
di: Zhang, Yusen
Pubblicazione: (2024)

CASK: Core-Aware Selective KV Compression for Reasoning Traces
di: Kim, Buseong, et al.
Pubblicazione: (2026)

Hyper-Compression: Model Compression via Hyperfunction
di: Fan, Fenglei, et al.
Pubblicazione: (2024)

Quantifying and Understanding Uncertainty in Large Reasoning Models
di: Li, Yangyi, et al.
Pubblicazione: (2026)

Hierarchical Autoencoder-based Lossy Compression for Large-scale High-resolution Scientific Data
di: Le, Hieu, et al.
Pubblicazione: (2023)

When Can LLMs Learn to Reason with Weak Supervision?
di: Rahman, Salman, et al.
Pubblicazione: (2026)

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression
di: Zhang, Te, et al.
Pubblicazione: (2025)

Point Cloud Compression with Bits-back Coding
di: Hieu, Nguyen Quang, et al.
Pubblicazione: (2024)

LightThinker++: From Reasoning Compression to Memory Management
di: Zhu, Yuqi, et al.
Pubblicazione: (2026)

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
di: Wang, Kai, et al.
Pubblicazione: (2025)

Large Language Model Compression with Global Rank and Sparsity Optimization
di: Zhou, Changhai, et al.
Pubblicazione: (2025)

ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning
di: Qiao, Ziqing, et al.
Pubblicazione: (2025)

Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation
di: Phan, Phuc, et al.
Pubblicazione: (2024)

MGAA: Multi-Granular Adaptive Allocation fof Low-Rank Compression of LLMs
di: Li, Guangyan, et al.
Pubblicazione: (2025)

Diffusion Generative Models Meet Compressed Sensing, with Applications to Imaging and Finance
di: Guo, Zhengyi, et al.
Pubblicazione: (2025)

To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration
di: Yang, Zeyu, et al.
Pubblicazione: (2025)

When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models
di: Wang, Weilan, et al.
Pubblicazione: (2025)

Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving
di: Gao, Wei, et al.
Pubblicazione: (2025)

Structural Rationale Distillation via Reasoning Space Compression
di: Yang, Jialin, et al.
Pubblicazione: (2026)

Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning
di: Zhang, Zheng
Pubblicazione: (2025)

Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks
di: Xu, Xingcheng, et al.
Pubblicazione: (2024)

SEE: Sememe Entanglement Encoding for Transformer-bases Models Compression
di: Zhang, Jing, et al.
Pubblicazione: (2024)

CoSA: Compressed Sensing-Based Adaptation of Large Language Models
di: Wei, Songtao, et al.
Pubblicazione: (2026)

PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
di: Li, Yilong, et al.
Pubblicazione: (2024)

Large Language Models Meet Graph Neural Networks for Text-Numeric Graph Reasoning
di: Song, Haoran, et al.
Pubblicazione: (2025)

Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models
di: Phan, Hoang, et al.
Pubblicazione: (2025)

AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models
di: Wang, Xiangqi, et al.
Pubblicazione: (2025)

Calibration-Aware Policy Optimization for Reasoning LLMs
di: Wang, Ziqi, et al.
Pubblicazione: (2026)

When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
di: Jeong, Soyeong, et al.
Pubblicazione: (2025)

SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression
di: Xu, Yuyang, et al.
Pubblicazione: (2025)

Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
di: Qu, Xingwei, et al.
Pubblicazione: (2025)

LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy
di: Zhang, Rongzhi, et al.
Pubblicazione: (2024)