Buchumschlag

Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Sheng, Zhichao, Zhou, Shilin, Gong, Chen, Li, Zhenghua
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models
von: Shen, Yi, et al.
Veröffentlicht: (2025)

Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning
von: Luo, Qin-Wen, et al.
Veröffentlicht: (2026)

UniSLU: Unified Spoken Language Understanding from Heterogeneous Cross-Task Datasets
von: Sheng, Zhichao, et al.
Veröffentlicht: (2025)

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

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model
von: Wan, Xu, et al.
Veröffentlicht: (2025)

Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
von: Guo, Zhenyuan, et al.
Veröffentlicht: (2026)

Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning
von: Jali, Neharika, et al.
Veröffentlicht: (2026)

Large Reasoning Models Learn Better Alignment from Flawed Thinking
von: Peng, ShengYun, et al.
Veröffentlicht: (2025)

Learning How Much to Think: Difficulty-Aware Dynamic MoEs for Graph Node Classification
von: Zhou, Jiajun, et al.
Veröffentlicht: (2026)

HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline
von: Li, Yang, et al.
Veröffentlicht: (2023)

Improving Contextual ASR via Multi-grained Fusion with Large Language Models
von: Zhou, Shilin, et al.
Veröffentlicht: (2025)

Toward Adaptive Reasoning in Large Language Models with Thought Rollback
von: Chen, Sijia, et al.
Veröffentlicht: (2024)

Learning When to Think While Listening in Large Audio-Language Models
von: Song, Zhiyuan, et al.
Veröffentlicht: (2026)

Large Language Models as Analogical Reasoners
von: Yasunaga, Michihiro, et al.
Veröffentlicht: (2023)

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

Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs
von: Li, Xueyan, et al.
Veröffentlicht: (2025)

DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
von: Zhou, Yang, et al.
Veröffentlicht: (2026)

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

Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models
von: Xie, Zhifei, et al.
Veröffentlicht: (2025)

On the Thinking-Language Modeling Gap in Large Language Models
von: Liu, Chenxi, et al.
Veröffentlicht: (2025)

Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models
von: Huang, Xin, et al.
Veröffentlicht: (2025)

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning
von: Zhu, Yekun, et al.
Veröffentlicht: (2025)

ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking
von: Lin, Lequan, et al.
Veröffentlicht: (2025)

Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
von: Lotfi, Sanae, et al.
Veröffentlicht: (2026)

Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement Learning
von: Wan, Qian, et al.
Veröffentlicht: (2026)

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
von: Zhu, Zihao, et al.
Veröffentlicht: (2025)

Estimating Item Difficulty with Large Language Models as Experts
von: Kolesnikova, Diana, et al.
Veröffentlicht: (2026)

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
von: Fu, Tianyu, et al.
Veröffentlicht: (2025)

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
von: Liu, Chen, et al.
Veröffentlicht: (2021)

Design Principle Transfer in Neural Architecture Search via Large Language Models
von: Zhou, Xun, et al.
Veröffentlicht: (2024)

Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
von: Damani, Mehul, et al.
Veröffentlicht: (2024)

What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation
von: Gong, Zhuocheng, et al.
Veröffentlicht: (2024)

Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner
von: He, Tao, et al.
Veröffentlicht: (2025)

Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs
von: Yadav, Suraj, et al.
Veröffentlicht: (2026)

A Neuro-inspired Interpretation of Unlearning in Large Language Models through Sample-level Unlearning Difficulty
von: Feng, Xiaohua, et al.
Veröffentlicht: (2025)

MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning
von: Li, Xuchen, et al.
Veröffentlicht: (2026)

Adaptive Multi-Expert Reasoning via Difficulty-Aware Routing and Uncertainty-Guided Aggregation
von: Ehab, Mohamed, et al.
Veröffentlicht: (2026)

Localizing and Editing Knowledge in Large Audio-Language Models
von: Chung, Sung Kyun, et al.
Veröffentlicht: (2026)

MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoning
von: Xi, Ningyuan, et al.
Veröffentlicht: (2024)

Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models
von: Zhou, Zhanke, et al.
Veröffentlicht: (2025)