Image de couverture de livre

Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Xueyan, Zenn, Johannes, Fadeeva, Ekaterina, Su, Guinan, Sachan, Mrinmaya, Geiping, Jonas
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs
par: Li, Xueyan, et autres
Publié: (2025)

Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
par: Su, Guinan, et autres
Publié: (2026)

Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging
par: Su, Guinan, et autres
Publié: (2025)

Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models
par: Geiping, Jonas, et autres
Publié: (2025)

Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search
par: Fadeeva, Ekaterina, et autres
Publié: (2025)

When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs
par: Wang, Keyu, et autres
Publié: (2025)

Differentiable Annealed Importance Sampling Minimizes The Symmetrized Kullback-Leibler Divergence Between Initial and Target Distribution
par: Zenn, Johannes, et autres
Publié: (2024)

Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models
par: Tong, Yijie, et autres
Publié: (2026)

Efficiently Dispatching Flash Attention For Partially Filled Attention Masks
par: Sharma, Agniv, et autres
Publié: (2024)

Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing
par: Ozyurt, Yilmazcan, et autres
Publié: (2024)

What Do Language Models Learn in Context? The Structured Task Hypothesis
par: Li, Jiaoda, et autres
Publié: (2024)

Balancing Molecular Information and Empirical Data in the Prediction of Physico-Chemical Properties
par: Zenn, Johannes, et autres
Publié: (2024)

Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
par: Do, Heejin, et autres
Publié: (2026)

Variational Classification
par: Dhuliawala, Shehzaad, et autres
Publié: (2023)

A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data & Overparameterization?
par: Xiao, Tim Z., et autres
Publié: (2023)

When, Where and Why to Average Weights?
par: Ajroldi, Niccolò, et autres
Publié: (2025)

Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation
par: Shi, Minjing, et autres
Publié: (2026)

Improving Large Language Model Safety with Contrastive Representation Learning
par: Simko, Samuel, et autres
Publié: (2025)

Unveiling the Visual Counting Bottleneck in Vision-Language Models
par: Pang, Xingzhou, et autres
Publié: (2026)

Learning to Reason Efficiently with A* Post-Training
par: Opedal, Andreas, et autres
Publié: (2026)

Training Dynamics Impact Post-Training Quantization Robustness
par: Catalan-Tatjer, Albert, et autres
Publié: (2025)

SMART: Self-learning Meta-strategy Agent for Reasoning Tasks
par: Liu, Rongxing, et autres
Publié: (2024)

Towards Aligning Language Models with Textual Feedback
par: Lloret, Saüc Abadal, et autres
Publié: (2024)

Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling
par: Srećković, Teodora, et autres
Publié: (2025)

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
par: Wen, Yuxin, et autres
Publié: (2024)

Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling
par: Xiao, Tim Z., et autres
Publié: (2025)

Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
par: Daheim, Nico, et autres
Publié: (2024)

MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs
par: Opedal, Andreas, et autres
Publié: (2024)

Deterministic Exploration via Stationary Bellman Error Maximization
par: Griesbach, Sebastian, et autres
Publié: (2024)

Deterministic Reservoir Computing for Chaotic Time Series Prediction
par: Viehweg, Johannes, et autres
Publié: (2025)

$ϕ$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
par: Xu, Fangzhi, et autres
Publié: (2025)

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
par: Geiping, Jonas, et autres
Publié: (2025)

Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language Models
par: Elhassan, Fay, et autres
Publié: (2025)

Bayesian Inverse Problems Meet Flow Matching: Efficient and Flexible Inference via Transformers
par: Sherki, Daniil, et autres
Publié: (2025)

MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors
par: Macina, Jakub, et autres
Publié: (2025)

Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation
par: Liu, Tianyu, et autres
Publié: (2024)

Efficient Neural Compression with Inference-time Decoding
par: Metz, C., et autres
Publié: (2024)

Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning
par: Otth, Matthias, et autres
Publié: (2025)

ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
par: Ni, Jingwei, et autres
Publié: (2025)

Pitfalls in Evaluating Language Model Forecasters
par: Paleka, Daniel, et autres
Publié: (2025)