Cover Image

AdaSwitch: Balancing Exploration and Guidance in Knowledge Distillation via Adaptive Switching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Peng, Jingyu, Wang, Maolin, Cai, Hengyi, Li, Yuchen, Zhang, Kai, Wang, Shuaiqiang, Yin, Dawei, Zhao, Xiangyu
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning
by: Sun, Hao, et al.
Published: (2024)

MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
by: Qu, Changle, et al.
Published: (2026)

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
by: Qu, Changle, et al.
Published: (2024)

AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization
by: Li, Qiyang, et al.
Published: (2026)

AdaSwitch: An Adaptive Switching Meta-Algorithm for Learning-Augmented Bounded-Influence Problems
by: Chen, Xi, et al.
Published: (2025)

MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering
by: Wu, Hui, et al.
Published: (2026)

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
by: Wu, Jiayi, et al.
Published: (2024)

Efficient Thought Space Exploration Through Strategic Intervention
by: Li, Ziheng, et al.
Published: (2025)

AdaCS: Adaptive Normalization for Enhanced Code-Switching ASR
by: Chu, The Chuong, et al.
Published: (2025)

Tool Learning with Large Language Models: A Survey
by: Qu, Changle, et al.
Published: (2024)

Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression
by: Peng, Jingyu, et al.
Published: (2025)

Behavior-Equivalent Token: Single-Token Replacement for Long Prompts in LLMs
by: Dong, Jiancheng, et al.
Published: (2025)

GRAF: Multi-turn Jailbreaking via Global Refinement and Active Fabrication
by: Tang, Hua, et al.
Published: (2025)

XL$^2$Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies
by: Ni, Xuanfan, et al.
Published: (2024)

Reinforced Efficient Reasoning via Semantically Diverse Exploration
by: Zhao, Ziqi, et al.
Published: (2026)

MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
by: Jia, Pengyue, et al.
Published: (2023)

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
by: Hu, Yuezhou, et al.
Published: (2025)

Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation
by: Zhang, Hengran, et al.
Published: (2025)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
by: Zhang, Xiaoyun, et al.
Published: (2025)

Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models
by: Wu, Hui, et al.
Published: (2026)

SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset
by: Xie, Peng, et al.
Published: (2025)

Towards Verifiable Text Generation with Evolving Memory and Self-Reflection
by: Sun, Hao, et al.
Published: (2023)

AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures
by: Zhang, Situo, et al.
Published: (2024)

Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning
by: Zhao, Yukun, et al.
Published: (2025)

Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning
by: He, Yang, et al.
Published: (2025)

Beyond Mimicry to Contextual Guidance: Knowledge Distillation for Interactive AI
by: Wang, Tong, et al.
Published: (2024)

KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
by: Lyu, Yougang, et al.
Published: (2024)

MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning
by: Wang, Maolin, et al.
Published: (2025)

Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation
by: Zhu, Dongsheng, et al.
Published: (2025)

SwitchCIT: Switching for Continual Instruction Tuning
by: Wu, Xinbo, et al.
Published: (2024)

Cross-model Control: Improving Multiple Large Language Models in One-time Training
by: Wu, Jiayi, et al.
Published: (2024)

AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging
by: Zhao, Yiran, et al.
Published: (2024)

AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAG
by: Peng, Chao, et al.
Published: (2025)

ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models
by: Liu, Jing, et al.
Published: (2024)

Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation
by: Zhou, Yuhang, et al.
Published: (2024)

LLM-Oriented Token-Adaptive Knowledge Distillation
by: Xie, Xurong, et al.
Published: (2025)

AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge
by: Wang, Han, et al.
Published: (2024)

MixReasoning: Switching Modes to Think
by: Lu, Haiquan, et al.
Published: (2025)

SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration
by: Zhang, Xichen, et al.
Published: (2025)

AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting
by: Huang, Shijue, et al.
Published: (2025)