Cover Image

Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ji, Xiaotong, Tutunov, Rasul, Zimmer, Matthieu, Ammar, Haitham Bou
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
by: Nguyen, Tu, et al.
Published: (2026)

Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers
by: Ji, Xiaotong, et al.
Published: (2026)

The $\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $λ$-Calculus
by: Roy, Amartya, et al.
Published: (2026)

Bourbaki: Self-Generated and Goal-Conditioned MDPs for Theorem Proving
by: Zimmer, Matthieu, et al.
Published: (2025)

Risk-Controlled Lean-as-Judge for Natural-Language Mathematical Reasoning
by: Bourigault, Pauline, et al.
Published: (2026)

Rethinking Large Language Model Distillation: A Constrained Markov Decision Process Perspective
by: Zimmer, Matthieu, et al.
Published: (2025)

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
by: Ramesh, Shyam Sundhar, et al.
Published: (2026)

Model-Based and Sample-Efficient AI-Assisted Math Discovery in Sphere Packing
by: Tutunov, Rasul, et al.
Published: (2025)

Mixture of Attentions For Speculative Decoding
by: Zimmer, Matthieu, et al.
Published: (2024)

Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
by: Oomerjee, Adnan, et al.
Published: (2025)

SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
by: Christopoulou, Fenia, et al.
Published: (2024)

On Almost Surely Safe Alignment of Large Language Models at Inference-Time
by: Ji, Xiaotong, et al.
Published: (2025)

Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Information
by: Tutnov, Rasul, et al.
Published: (2025)

Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation
by: Fountas, Zafeirios, et al.
Published: (2026)

Human-inspired Episodic Memory for Infinite Context LLMs
by: Fountas, Zafeirios, et al.
Published: (2024)

Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
by: Diwan, Anish, et al.
Published: (2026)

Beyond Distribution Sharpening: The Importance of Task Rewards
by: Mittal, Sarthak, et al.
Published: (2026)

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
by: Liu, Mingjie, et al.
Published: (2025)

Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods
by: Benfeghoul, Martin, et al.
Published: (2025)

Subjective Depth and Timescale Transformers: Learning Where and When to Compute
by: Wieser, Frederico, et al.
Published: (2025)

PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching
by: Chen, Ruishuo, et al.
Published: (2026)

Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching
by: Gupta, Aditi, et al.
Published: (2026)

SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning
by: Hazard, Hugo, et al.
Published: (2025)

Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning
by: Huang, Bingning, et al.
Published: (2025)

Training Long-Context LLMs Efficiently via Chunk-wise Optimization
by: Li, Wenhao, et al.
Published: (2025)

Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning
by: Altabaa, Awni, et al.
Published: (2025)

Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
by: Ahmed, Ammar, et al.
Published: (2025)

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration
by: Deng, Wenhao, et al.
Published: (2025)

SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning
by: Do, Dai, et al.
Published: (2025)

Train Long, Think Short: Curriculum Learning for Efficient Reasoning
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

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

Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
by: Xie, Pei-Xi, et al.
Published: (2026)

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

Sample Efficient Preference Alignment in LLMs via Active Exploration
by: Mehta, Viraj, et al.
Published: (2023)

Domain-Grounded Evaluation of LLMs in International Student Knowledge
by: Daitx, Claudinei, et al.
Published: (2025)

Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning
by: Di, Zixiang, et al.
Published: (2026)

Al-Khwarizmi: Discovering Physical Laws with Foundation Models
by: Mower, Christopher E., et al.
Published: (2025)

Data-Efficient Training by Evolved Sampling
by: Cheng, Ziheng, et al.
Published: (2025)

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning
by: Zhang, Junru, et al.
Published: (2025)

DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning
by: Zhao, Hanyang, et al.
Published: (2025)