No article text was recorded for this version.
best-of-n sampling
Version 1 of 1279 papers320 conceptsfrozen 2026-10-04
Papers in this version
- Blog: DRIVE: Distributional and Retrieval-Augmented Bidding with Value Evaluation
- Blog: Aligning Large Language Models by On-Policy Self-Judgment
- Blog: Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline Settings
- Blog: Simple Ingredients for Offline Reinforcement Learning
- Blog: CycleResearcher: Improving Automated Research via Automated Review
- Blog: Neural Quality Estimation of Grammatical Error Correction
- Blog: Enabling Large Language Models to Generate Text with Citations
- Blog: RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question
- Blog: GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation
- Blog: Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
- Blog: Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task
- Blog: CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction
- Blog: Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads
- Blog: ACE-RLHF: Automated Code Evaluation and Socratic Feedback Generation Tool using Large Language Models and Reinforcement Learning with Human Feedback
- Blog: Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction
- Blog: Efficient Diffusion Policies For Offline Reinforcement Learning
- Blog: OFER: Occluded Face Expression Reconstruction
- Blog: DreamPRM: Domain-reweighted Process Reward Model for Multimodal Reasoning
- Blog: WebGPT: Browser-assisted question-answering with human feedback
- Blog: BoKDiff: Best-of-K Diffusion Alignment for Target-Specific 3D Molecule Generation
- Blog: Guiding ChatGPT to Generate Salient Domain Summaries
- Blog: Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models
- Blog: Q-value Regularized Transformer for Offline Reinforcement Learning
- Blog: Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
- Blog: CodePDE: An Inference Framework for LLM-driven PDE Solver Generation
- Blog: VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR
- Blog: Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation
- Blog: PhyCritic: Multimodal Critic Models for Physical AI
- Blog: Reranking-based Generation for Unbiased Perspective Summarization
- Blog: CycleResearcher: Improving Automated Research via Automated Review
- Blog: VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation
- Blog: Learning Preference Model for LLMs via Automatic Preference Data Generation
- Blog: Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
- Blog: Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
- Blog: Discriminative Visual Process Rewards for Scaling Thinking at Test-Time with Images
- Blog: RMB: Comprehensively benchmarking reward models in LLM alignment
- Blog: Critic Regularized Regression
- Blog: GTA1: GUI Test-time Scaling Agent
- Blog: Habitizing Diffusion Planning for Efficient and Effective Decision Making
- Blog: UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
- Blog: Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression
- Blog: Improving alignment of dialogue agents via targeted human judgements
- Blog: Inverse-RLignment: Inverse Reinforcement Learning from Demonstrations for LLM Alignment
- Blog: STaR-SQL: Self-Taught Reasoner for Text-to-SQL
- Blog: TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation
- Blog: Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents
- Blog: Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
- Blog: When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers
- Blog: Automatic Prompt Selection for Large Language Models
- Blog: AI capabilities can be significantly improved without expensive retraining
- Blog: Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models
- Blog: RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
- Blog: Robust Preference Alignment via Directional Neighborhood Consensus
- Blog: Fake it till You Make it: Reward Modeling as Discriminative Prediction
- Blog: Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
- Blog: P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
- Blog: Aligning Text-to-Image Models using Human Feedback
- Blog: Improving Reading Comprehension Question Generation with Data Augmentation and Overgenerate-and-rank
- Blog: MathArena: Evaluating LLMs on Uncontaminated Math Competitions
- Blog: Team ISM at CLPsych 2025: Capturing Mental Health Dynamics from Social Media Timelines using A Pretrained Large Language Model with In-Context Learning
Showing 60 of 279 papers.
History & citation
Current · Permanent link
- Reward Guided Inference for Scaling Model Performance merged into this direction (60% overlap)
- Post-Generation Reranking for Enhanced Model Quality merged into this direction (53% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_best_of_n_sampling_6c122eec,
title = {best-of-n sampling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/best-of-n-sampling/rdr_6c122eecdaa04a61b1cd2be6437e7e49},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_best_of_n_sampling_6c122eec_v1,
title = {best-of-n sampling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/best-of-n-sampling/rdr_6c122eecdaa04a61b1cd2be6437e7e49/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}