Copertina

A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Xiaoang, Wang, Shuo, Han, Xu, Liu, Zhenghao, Wu, Huijia, Li, Peipei, Liu, Zhiyuan, Sun, Maosong, He, Zhaofeng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs
di: Wu, Dingjun, et al.
Pubblicazione: (2025)

KBAlign: Efficient Self Adaptation on Specific Knowledge Bases
di: Zeng, Zheni, et al.
Pubblicazione: (2024)

Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
di: Liu, Zhenghao, et al.
Pubblicazione: (2026)

Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
di: Ping, Bowen, et al.
Pubblicazione: (2024)

Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
di: Wang, Dianyun, et al.
Pubblicazione: (2025)

Legal$Δ$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
di: Dai, Xin, et al.
Pubblicazione: (2025)

CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal Devices
di: Zhao, Weilin, et al.
Pubblicazione: (2023)

Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
di: Peng, Chunyi, et al.
Pubblicazione: (2025)

Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection
di: Wu, Zhuoyang, et al.
Pubblicazione: (2025)

LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
di: Wang, Hanqing, et al.
Pubblicazione: (2024)

VisRAG 2.0: Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation
di: Sun, Yubo, et al.
Pubblicazione: (2025)

UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset
di: Wang, Haoyu, et al.
Pubblicazione: (2024)

Training Large Reasoning Models Efficiently via Progressive Thought Encoding
di: Zhang, Zeliang, et al.
Pubblicazione: (2026)

ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning
di: Hu, Minda, et al.
Pubblicazione: (2026)

Efficient Reasoning via Chain of Unconscious Thought
di: Gong, Ruihan, et al.
Pubblicazione: (2025)

DeepNote: Note-Centric Deep Retrieval-Augmented Generation
di: Wang, Ruobing, et al.
Pubblicazione: (2024)

FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection
di: Huang, Yufei, et al.
Pubblicazione: (2024)

VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
di: Yu, Shi, et al.
Pubblicazione: (2024)

RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework
di: Zhu, Kunlun, et al.
Pubblicazione: (2024)

Efficient Reasoning via Thought-Training and Thought-Free Inference
di: Wu, Canhui, et al.
Pubblicazione: (2025)

Reasoning Efficiently Through Adaptive Chain-of-Thought Compression: A Self-Optimizing Framework
di: Huang, Kerui, et al.
Pubblicazione: (2025)

Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models
di: Liu, Shuodi, et al.
Pubblicazione: (2025)

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
di: Yang, Zhiyu, et al.
Pubblicazione: (2024)

APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
di: Huang, Yuxiang, et al.
Pubblicazione: (2025)

StateX: Enhancing RNN Recall via Post-training State Expansion
di: Shen, Xingyu, et al.
Pubblicazione: (2025)

METEOR: Evolutionary Journey of Large Language Models from Guidance to Self-Growth
di: Li, Jiawei, et al.
Pubblicazione: (2024)

Reasoning Beyond Chain-of-Thought: A Latent Computational Mode in Large Language Models
di: He, Zhenghao, et al.
Pubblicazione: (2026)

ConPET: Continual Parameter-Efficient Tuning for Large Language Models
di: Song, Chenyang, et al.
Pubblicazione: (2023)

Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
di: Liu, Shuliang, et al.
Pubblicazione: (2025)

Dynamic Generation of Personalities with Large Language Models
di: Liu, Jianzhi, et al.
Pubblicazione: (2024)

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation
di: Chen, Hao, et al.
Pubblicazione: (2025)

Faithful Logical Reasoning via Symbolic Chain-of-Thought
di: Xu, Jundong, et al.
Pubblicazione: (2024)

Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models
di: Liu, Yule, et al.
Pubblicazione: (2025)

Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules
di: Xiao, Chaojun, et al.
Pubblicazione: (2023)

Stuffed Mamba: Oversized States Lead to the Inability to Forget
di: Chen, Yingfa, et al.
Pubblicazione: (2024)

OneBit: Towards Extremely Low-bit Large Language Models
di: Xu, Yuzhuang, et al.
Pubblicazione: (2024)

LLM$\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources
di: Wang, Haoyu, et al.
Pubblicazione: (2025)

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
di: Cheng, Jeffrey, et al.
Pubblicazione: (2024)

Canvas-of-Thought: Grounding Reasoning via Mutable Structured States
di: Sun, Lingzhuang, et al.
Pubblicazione: (2026)

States Hidden in Hidden States: LLMs Emerge Discrete State Representations Implicitly
di: Chen, Junhao, et al.
Pubblicazione: (2024)