Copertina

RAST: Reasoning Activation in LLMs via Small-model Transfer

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ouyang, Siru, Zhu, Xinyu, Xiao, Zilin, Jiang, Minhao, Meng, Yu, Han, Jiawei
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

Investigating Data Contamination for Pre-training Language Models
di: Jiang, Minhao, et al.
Pubblicazione: (2024)

FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models
di: Liu, Xuan, et al.
Pubblicazione: (2025)

RAST: A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction
di: Ruan, Weilin, et al.
Pubblicazione: (2025)

ProxyThinker: Test-Time Guidance through Small Visual Reasoners
di: Xiao, Zilin, et al.
Pubblicazione: (2025)

Evaluating Reasoning LLMs for Suicide Screening with the Columbia-Suicide Severity Rating Scale
di: Patil, Avinash, et al.
Pubblicazione: (2025)

CoRAST: Towards Foundation Model-Powered Correlated Data Analysis in Resource-Constrained CPS and IoT
di: Hu, Yi, et al.
Pubblicazione: (2024)

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
di: Han, Pengrui, et al.
Pubblicazione: (2026)

Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning
di: Fang, Yin, et al.
Pubblicazione: (2025)

ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs
di: Zhang, Zhengyan, et al.
Pubblicazione: (2024)

From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph
di: Gong, Junfeng, et al.
Pubblicazione: (2025)

ActivationReasoning: Logical Reasoning in Latent Activation Spaces
di: Helff, Lukas, et al.
Pubblicazione: (2025)

Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures
di: He, Yu, et al.
Pubblicazione: (2025)

CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs
di: Skelic, Lejla, et al.
Pubblicazione: (2025)

ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation
di: Meng, Chuiyang, et al.
Pubblicazione: (2026)

Relative Policy-Transition Optimization for Fast Policy Transfer
di: Xu, Jiawei, et al.
Pubblicazione: (2022)

Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control
di: Sheng, Zihao, et al.
Pubblicazione: (2024)

How Should LLMs Consume High-Quality Data? Optimal Data Scheduling via Quality-Aware Functional Scaling Laws
di: Zhu, Zhitao, et al.
Pubblicazione: (2026)

Predicting LLM Reasoning Performance with Small Proxy Model
di: Koh, Woosung, et al.
Pubblicazione: (2025)

Test-time Diverse Reasoning by Riemannian Activation Steering
di: Khanh, Ly Tran Ho, et al.
Pubblicazione: (2025)

Robust Knowledge Transfer in Tiered Reinforcement Learning
di: Huang, Jiawei, et al.
Pubblicazione: (2023)

Process In-Context Learning: Enhancing Mathematical Reasoning via Dynamic Demonstration Insertion
di: Gao, Ang, et al.
Pubblicazione: (2026)

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
di: Kang, Minjae, et al.
Pubblicazione: (2026)

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
di: Yue, Murong, et al.
Pubblicazione: (2024)

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
di: Agarwal, Shivam, et al.
Pubblicazione: (2025)

Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation
di: Tian, Yijun, et al.
Pubblicazione: (2024)

Temporal Sampling for Forgotten Reasoning in LLMs
di: Li, Yuetai, et al.
Pubblicazione: (2025)

AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection
di: Zhang, Junru, et al.
Pubblicazione: (2026)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
di: Jiang, Xinyan, et al.
Pubblicazione: (2026)

Leveraging Parameter Space Symmetries for Reasoning Skill Transfer in LLMs
di: Horoi, Stefan, et al.
Pubblicazione: (2025)

Safety Reasoning with Guidelines
di: Wang, Haoyu, et al.
Pubblicazione: (2025)

Transfer Learning for Diffusion Models
di: Ouyang, Yidong, et al.
Pubblicazione: (2024)

Frontier LLMs Still Struggle with Simple Reasoning Tasks
di: Malek, Alan, et al.
Pubblicazione: (2025)

Can only LLMs do Reasoning?: Potential of Small Language Models in Task Planning
di: Choi, Gawon, et al.
Pubblicazione: (2024)

Broken Chains: The Cost of Incomplete Reasoning in LLMs
di: Su, Ian, et al.
Pubblicazione: (2026)

ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning
di: Liu, Zexi, et al.
Pubblicazione: (2025)

Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs
di: Zhang, Dingkun, et al.
Pubblicazione: (2025)

Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
di: Fan, Jiajun, et al.
Pubblicazione: (2025)

CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation
di: Liu, Ziyue, et al.
Pubblicazione: (2025)

A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis
di: Gao, Xin, et al.
Pubblicazione: (2025)

Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward
di: Wen, Xuexiang, et al.
Pubblicazione: (2026)