RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS

1952/01/01 by RALPH ALLAN BRADLEY, Ralph A. Bradley, Milton E. Terry +1 · 1,382 citations
Economics, Econometrics and Finance · Engineering · Mathematics · #Block (permutation group theory) #Combinatorics #Credit Risk and Financial Regulations #Mathematics #Modeling, Simulation, and Optimization #Rank (graph theory) #Statistics #VLSI and FPGA Design Techniques

paper · doi:10.1093/biomet/39.3-4.324

published in Biometrika 39(3-4), 324-345 (Oxford University Press)

openalex publication_date 1952/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/02

Cited by

• Perceiving Protest: How Publics View the Disruptiveness and Effectiveness of Protest
• Convergence analysis of a family of Zermelo-type iterations for the Bradley--Terry model
• RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences
• Evaluating Risks in Weak-to-Strong Alignment: A Bias-Variance Perspective
• When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines
• Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels
• Rater State Bias in RLHF Preference Data: An Audit Framework
• OR Else: A Differentiable Trust Region for Policy Optimization
• Style over Substance: A Shortcut Audit of Emotion-Description Preference Evaluation
• Rationalizing Boltzmann Rationality: An Axiomatic Characterization of Entropy-Regularized Policies
• A Method for Learning Value Systems in Generative AI
• When Can You Debias an LLM Judge? Identifiability Limits, a Test, and Designs for Top-k Ranking
• TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue
• Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling
• SODA: Semi On-Policy Black-Box Distillation for Large Language Models
• Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function
• Multi-Turn On-Policy Distillation with Prefix Replay
• Risk-Aware Preference Learning for Stochastic Outcomes
• Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning
• From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language
• Robust Critics: Defending LLMs Against Multi-Turn Attacks
• When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance
• Large-scale online deanonymization with LLMs
• Measuring Scalar Constructs in Social Science with LLMs
• ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering
• LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing
• Robin: A multi-agent system for automating scientific discovery
• Base Models Beat Aligned Models at Randomness and Creativity
• Explaining Human Preferences via Metrics for Structured 3D Reconstruction
• Decoding-based Regression
• Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings
• Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
• Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision
• SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models
• What do Reward Models Memorize?
• GEMCo: A Validated, Ethically Releasable Proxy for Inaccessible Counselling Data
• Simulating Single Transferable Voting for the Colorado House of Representatives
• Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
• Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining
• VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing
• Group Preference Collapse in Personalized Multimodal Large Language Models
• Mean-Field Analysis and Optimal Control of a Dynamic Rating and Matchmaking System
• SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams
• Statistical and computational challenges in ranking
• Safety Alignment of LMs via Non-cooperative Games
• Counterfactual LLM-based Framework for Measuring Rhetorical Style
• From Pixels to Predicates Structuring urban perception with scene graphs
• Efficient Personalization of Generative Models via Optimal Experimental Design
• Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game
• Model inference for ranking from pairwise comparisons
• Vibe Spaces for Creatively Connecting and Expressing Visual Concepts
• DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization
• Estimating problem difficulty without ground truth using Large Language Model comparisons
• Explainable reinforcement learning from human feedback to improve alignment
• ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement
• Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided Reflection
• From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
• LLMs Can Assist with Proposal Selection at Large User Facilities
• RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems
• Multi-dimensional Preference Alignment by Conditioning Reward Itself
• T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground
• Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment
• AgentComp: From Agentic Reasoning to Compositional Mastery in Text-to-Image Models
• Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE
• Statistical analysis of Inverse Entropy-regularized Reinforcement Learning
• Learning Preferences and User Engagement Using Choice and Time Data
• When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models
• DEAR: Dataset for Evaluating the Aesthetics of Rendering
• SA-IQA: Redefining Image Quality Assessment for Spatial Aesthetics with Multi-Dimensional Rewards
• Overcoming State Inertia: Minimally Invasive Temporal Alignment for Evolving Contexts
• Joint Progression Modeling (JPM): A Probabilistic Framework for Mixed-Pathology Progression
• Hypothesis Testing for Generalized Thurstone Models
• Distillability of LLM Security Logic: Predicting Attack Success Rate of Outline Filling Attack via Ranking Regression
• UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking
• When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF
• RecruitView: A Multimodal Dataset for Predicting Personality and Interview Performance for Human Resources Applications
• A Trainable Centrality Framework for Modern Data
• FLAWS: A Benchmark for Error Identification and Localization in Scientific Papers
• Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization
• Video Generation Models Are Good Latent Reward Models
• GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs
• Test-Time Preference Optimization for Image Restoration
• SmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data
• What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity
• Aligning Generative Music AI with Human Preferences: Methods and Challenges
• The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation
• Exploring question answering: metric analysis and evaluation framework for enhanced interpretability
• Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
• Maximizing the efficiency of human feedback in AI alignment: a comparative analysis
• Mitigating Length Bias in RLHF through a Causal Lens
• MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization
• PIRA: Preference-Oriented Instruction-Tuned Reward Models with Dual Aggregation
• Moment estimation in paired comparison models with a growing number of subjects
• Black-Box On-Policy Distillation of Large Language Models
• AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment
• Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation
• SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories
• Test-driven Reinforcement Learning in Continuous Control
• SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
• HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection
• SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization
• Characterizing AI Manipulation Risks in Brazilian YouTube Climate Discourse
• Ties in Paired-Comparison Experiments: A Generalization of the Bradley-Terry Model
• CPO: Condition Preference Optimization for Controllable Image Generation
• Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark
• Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models
• The Bradley-Terry Stochastic Block Model
• Speech-Based Prioritization for Schizophrenia Intervention
• From Measurement to Expertise: Empathetic Expert Adapters for Context-Based Empathy in Conversational AI Agents
• Human-AI Collaboration with Misaligned Preferences
• Automated Reward Design for Gran Turismo
• Toward Objective and Interpretable Prosody Evaluation in Text-to-Speech: A Linguistically Motivated Approach
• Deployable Vision-driven UAV River Navigation via Human-in-the-loop Preference Alignment
• ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations
• MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models
• Value Drifts: Tracing Value Alignment During LLM Post-Training
• Offline Clustering of Preference Learning with Active-data Augmentation
• One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning
• E-Scores for (In)Correctness Assessment of Generative Model Outputs
• Wilks' theorems in some exponential random graph models
• Mediocrity is the key for LLM as a Judge Anchor Selection
• Default Bayes factors for ANOVA designs
• Reward Models are Metrics in a Trench Coat
• Estimation from Pairwise Comparisons: Sharp Minimax Bounds with Topology Dependence
• Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
• Prior Distributions for the Bradley-Terry Model of Paired Comparisons
• Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
• Generative Bayesian Optimization: Generative Models as Acquisition Functions
• GReF: A Unified Generative Framework for Efficient Reranking via Ordered Multi-token Prediction
• Learning Video-Story Composition via Recurrent Neural Network
• Greedy Sampling Is Provably Efficient for RLHF
• PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
• Semi-Supervised Preference Optimization with Limited Feedback
• Fortytwo: Swarm Inference with Peer-Ranked Consensus
• GIFT: Group-relative Implicit Fine Tuning Integrates GRPO with DPO and UNA
• Protein Language Model Fitness Is a Matter of Preference
• The Burden of Interactive Alignment with Inconsistent Preferences
• Debiasing Reward Models by Representation Learning with Guarantees
• Lightweight Robust Direct Preference Optimization
• RobotArena ∞: Scalable Robot Benchmarking via Real-to-Sim Translation
• POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
• Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
• Learning "Partner-Aware" Collaborators in Multi-Party Collaboration
• Estimating the Error of Large Language Models at Pairwise Text Comparison
• Generalized Top-k Mallows Model for Ranked Choices
• Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models
• Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning
• Weak-to-Strong Generalization under Distribution Shifts
• Grouped sparse paired comparisons in the Bradley-Terry model
• Self-evolving expertise in complex non-verifiable subject domains: dialogue as implicit meta-RL
• Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
• Capturing Intransitive Dominance in Tennis Forecasting: A Graph Neural Network Approach
• Ask a Strong LLM Judge when Your Reward Model is Uncertain
• Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
• Why DPO is a Misspecified Estimator and How to Fix It
• Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
• Rectifying Shortcut Behaviors in Preference-based Reward Learning
• Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
• Pairwise Choice Markov Chains
• Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback
• ADPO: Anchored Direct Preference Optimization
• DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
• Cultural Alien Sampler: Open-ended art generation balancing originality and coherence
• Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling
• Eliciting Truthful Feedback for Preference-Based Learning via the VCG Mechanism
• Dual-Weighted Reinforcement Learning for Generative Preference Modeling
• Voting with the Graph: Stable RLAIF via Topological Consistency Maximization
• GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery
• Budget-aware Test-time Scaling via Discriminative Verification
• Confidence as a Reward: Transforming LLMs into Reward Models
• Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking
• Towards Understanding Valuable Preference Data for Large Language Model Alignment
• On the Role of Preference Variance in Preference Optimization
• Single Image Deraining: From Model-Based to Data-Driven and Beyond
• DocReward: A Document Reward Model for Structuring and Stylizing
• APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport
• Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation
• Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval
• RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model
• Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey
• Efficient Bayesian Inference from Noisy Pairwise Comparisons
• Users as Annotators: LLM Preference Learning from Comparison Mode
• Score-Based Density Estimation from Pairwise Comparisons
• Active Model Selection for Large Language Models
• What Makes a Visualization Image Complex?
• Contrastive Weak-to-strong Generalization
• OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
• From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation
• Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain
• Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
• Towards Better Optimization For Listwise Preference in Diffusion Models
• Optimal Stopping vs Best-of-N for Inference Time Optimization
• Model-free Rank Aggregation in the Presence of Rater Heterogeneity: A Maximum Score Approach
• Online Rubrics Elicitation from Pairwise Comparisons
• Reward Model Perspectives: Whose Opinions Do Reward Models Reward?
• Provably Convergent Primal-Dual DPO for Constrained LLM Alignment
• On the Role of Difficult Prompts in Self-Play Preference Optimization
• Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment
• Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization
• From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
• SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator
• Aligning Language Models with Clinical Expertise: DPO for Heart Failure Nursing Documentation in Critical Care
• BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks
• Best of mini-N in-loop Sampling: A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling
• LegalSim: Multi-Agent Simulation of Legal Systems for Discovering Procedural Exploits
• CVSM: Contrastive Vocal Similarity Modeling
• Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
• Hybrid-MST: A Hybrid Active Sampling Strategy for Pairwise Preference Aggregation
• From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modeling
• AP2O-Coder: Adaptively Progressive Preference Optimization for Reducing Compilation and Runtime Errors in LLM-Generated Code
• Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
• Judging with Confidence: Calibrating Autoraters to Preference Distributions
• GRPO-λ: Credit Assignment improves LLM Reasoning
• Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation
• fev-bench: A Realistic Benchmark for Time Series Forecasting
• Alignment-Aware Decoding
• Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation
• RAGferee: Building Contextual Reward Models for Retrieval-Augmented Generation
• RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity
• Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs
• Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis
• Information Design With Large Language Models
• Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference Optimization
• Generative Value Conflicts Reveal LLM Priorities
• OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
• RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment
• Meta-Router: Bridging Gold-standard and Preference-based Evaluations in Large Language Model Routing
• Interactive Groupwise Comparison for Reinforcement Learning from Human Feedback
• Preference-Based Dynamic Ranking Structure Recognition
• STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
• Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
• AI can help humans find common ground in democratic deliberation
• Tagging the Thought: Unlocking Personalization Reasoning via Reinforcement Learning
• General Exploratory Bonus for Optimistic Exploration in RLHF
• Multiplayer Nash Preference Optimization
• Adaptive Margin RLHF via Preference over Preferences
• Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback
• Think Socially via Cognitive Reasoning
• Preference-Guided Learning for Sparse-Reward Multi-Agent Reinforcement Learning
• X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning
• Failure Modes of Maximum Entropy RLHF
• Future Policy Aware Preference Learning for Mathematical Reasoning
• Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation
• MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation
• MedLLM: An Open Medical Language Model at the Sub-Billion Scale
• Implicit Safety Alignment from Crowd Preferences
• Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
• HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models
• Beyond Brightening Low-light Images
• Mathematicians’ Assessments of the Explanatory Value of Proofs
• Optimal Pairwise Comparison Procedures for Subjective Evaluation
• Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
• Similarity Field Theory: A Mathematical Framework for Intelligence
• Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization
• Dynamic Classifier-Free Diffusion Guidance via Online Feedback
• GPO: Learning from Critical Steps to Improve LLM Reasoning
• Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories
• Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
• siDPT: siRNA Efficacy Prediction via Debiased Preference-Pair Transformer
• Aligning Audio Captions with Human Preferences
• Estimating Semantic Alphabet Size for LLM Uncertainty Quantification
• Force-Modulated Visual Policy for Robot-Assisted Dressing with Arm Motions
• zELO: ELO-inspired Training Method for Rerankers and Embedding Models
• Designing Rules to Pick a Rule: Aggregation by Consistency
• Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
• Pluralistic Off-policy Evaluation and Alignment
• What Matters in Data for DPO?
• ToolRM: Outcome Reward Models for Tool-Calling Large Language Models
• When Are Two RLHF Objectives the Same?
• Term2Note: Synthesising Differentially Private Clinical Notes from Medical Terms
• Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens
• Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration
• Compass-v3: Scaling Domain-Specific LLMs for Multilingual E-Commerce in Southeast Asia
• Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling
• RewardDance: Reward Scaling in Visual Generation
• Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling
• CM-Align: Consistency-based Multilingual Alignment for Large Language Models
• Towards Generalized Routing: Model and Agent Orchestration for Adaptive and Efficient Inference
• Verbalized Algorithms: Classical Algorithms are All You Need (Mostly)
• Continuous Audio Language Models
• Let's Roleplay: Examining LLM Alignment in Collaborative Dialogues
• Legislators’ sentiment analysis supervised by legislators
• Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment
• Connections between reinforcement learning with feedback,test-time scaling, and diffusion guidance: An anthology
• GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models
• Post Hoc Regression Refinement via Pairwise Rankings
• A Foundation Model for Chest X-ray Interpretation with Grounded Reasoning via Online Reinforcement Learning
• SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences
• Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
• Adaptive Preference Optimization with Uncertainty-aware Utility Anchor
• IDEAlign: Comparing Large Language Models to Human Experts in Open-ended Interpretive Annotations
• Towards Reasoning for PDE Foundation Models: A Reward-Model-Driven Inference-Time-Scaling Algorithm
• MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols
• Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework
• Benchmarking Large Language Models for Personalized Guidance in AI-Enhanced Learning
• GRAM-R²: Self-Training Generative Foundation Reward Models for Reward Reasoning
• MPO: Multidimensional Preference Optimization for Language Model-based Text-to-Speech
• RPRO: Ranked Preference Reinforcement Optimization for Enhancing Medical QA and Diagnostic Reasoning
• ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics
• Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models
• Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation
• Brain-Inspired Deep Networks for Image Aesthetics Assessment
• OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning
• Interestingness First Classifiers
• Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
• Optimization Transfer Using Surrogate Objective Functions
• Search-Based Credit Assignment for Offline Preference-Based Reinforcement Learning
• Learning from Preferences and Mixed Demonstrations in General Settings
• Bridging Human and LLM Judgments: Understanding and Narrowing the Gap
• QuarkMed Medical Foundation Model Technical Report
• Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings
• Controlling Multimodal LLMs via Reward-guided Decoding
• Inclusion Arena: An Open Platform for Evaluating Large Foundation Models with Real-World Apps
• Fusing Rewards and Preferences in Reinforcement Learning
• Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization
• Performance of GPT-5 Frontier Models in Ophthalmology Question Answering
• On Negative-aware Preference Optimization for Recommendation
• Interpretable Reward Model via Sparse Autoencoder
• Who Pays the RENT? Implications of Spatial Inequality for Prediction-Based Allocation Policies
• Personalized Recommendations via Active Utility-based Pairwise Sampling
• Street-Level AI: Are Large Language Models Ready for Real-World Judgments?
• WeChat-YATT: A Scalable, Simple, Efficient, and Production Ready Training Library
• \(X\)-evolve: Solution space evolution powered by large language models
• Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment
• Data Selection for LLM Alignment Using Fine-Grained Preferences
• Pref-GUIDE: Continual Policy Learning from Real-Time Human Feedback via Preference-Based Learning
• Latent Preference Bandits
• Posterior-GRPO: Rewarding Reasoning Processes in Code Generation
• Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models
• FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data
• Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap
• HPSv3: Towards Wide-Spectrum Human Preference Score
• Alleviating Attention Hacking in Discriminative Reward Modeling through Interaction Distillation
• HALO: Human Preference Aligned Offline Reward Learning for Robot Navigation
• VAGPO: Vision-augmented Asymmetric Group Preference Optimization for Graph Routing Problems
• BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluation
• Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders
• Comparison of Large Language Models for Deployment Requirements
• G-Core: A Simple, Scalable and Balanced RLHF Trainer
• Post-Training Large Language Models via Reinforcement Learning from Self-Feedback
• Libra: Assessing and Improving Reward Model by Learning to Think
• Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback
• TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
• Multimodal LLMs as Customized Reward Models for Text-to-Image Generation
• Music Arena: Live Evaluation for Text-to-Music
• TADT-CSA: Temporal Advantage Decision Transformer with Contrastive State Abstraction for Generative Recommendation
• MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
• Can AI Model the Complexities of Human Moral Decision-making? A Qualitative Study of Kidney Allocation Decisions
• PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training
• Designing User-Centric Metrics for Evaluation of Counterfactual Explanations
• RobotValues: Evaluating Household Robots When Human Values Conflict
• MathDuels: Evaluating LLMs as Problem Posers and Solvers
• V₁: Unifying Generation and Self-Verification for Parallel Reasoners
• Statistical and Algorithmic Foundations of Reinforcement Learning
• Preference-based Multi-Objective Reinforcement Learning
• Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks
• Food and Food-Odor Preferences in Dogs: A Pilot Study
• Making Language Model a Hierarchical Classifier
• Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
• PrefPalette: Personalized Preference Modeling with Latent Attributes
• Learning to summarize user information for personalized reinforcement learning from human feedback
• Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese
• QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval
• EnlightenGAN: Deep Light Enhancement Without Paired Supervision
• ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
• On Monotonicity in AI Alignment
• GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO
• Optimal Differentially Private Ranking from Pairwise Comparisons
• Generalizing while preserving monotonicity in comparison-based preference learning models
• Mallows Model with Learned Distance Metrics: Sampling and Maximum Likelihood Estimation
• Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
• Principled Foundations for Preference Optimization
• Stable Preference Optimization: A Bilevel Approach to Catastrophic Preference Shift
• Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization
• Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
• Why is Your Language Model a Poor Implicit Reward Model?
• Divergence Minimization Preference Optimization for Diffusion Model Alignment
• Reward Models Can Improve Themselves: Reward-Guided Adversarial Failure Mode Discovery for Robust Reward Modeling
• Interpretable Reward Modeling with Active Concept Bottlenecks
• Learning Latent Reasoning Traces for Scalar Reward Models End-to-End
• News Source Citing Patterns in AI Search Systems
• wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
• Discrete Diffusion Trajectory Alignment via Stepwise Decomposition
• Pre-Trained Policy Discriminators are General Reward Models
• Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
• Agreement Is Not Quality: Blind Expert Verification of Human and LLM Qualitative Coding When Human Consensus Is Not Ground Truth
• Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity
• GenAI-Powered Inference
• Listwise Preference Alignment Optimization for Tail Item Recommendation
• Data Diversification Methods In Alignment Enhance Math Performance In LLMs
• MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining
• Confidence and Stability of Global and Pairwise Scores in NLP Evaluation
• Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual Disabilities
• Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models
• Residual Reward Models for Preference-based Reinforcement Learning
• SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks
• Linearly Decoding Refused Knowledge in Aligned Language Models
• FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes
• Generalist Reward Models: Found Inside Large Language Models
• The Hidden Link Between RLHF and Contrastive Learning
• Explicit Preference Optimization: No Need for an Implicit Reward Model
• Preference Completion: Large-scale Collaborative Ranking from Pairwise Comparisons
• Listwise Direct Preference Optimization with Multi-Dimensional Preference Mixing
• Data-driven satisficing measure and ranking
• Benchmarking Music Generation Models and Metrics via Human Preference Studies
• TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer
• LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
• 3D Arena: An Open Platform for Generative 3D Evaluation
• The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical Proofs
• Shrinking the Generation-Verification Gap with Weak Verifiers
• RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies
• Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque
• Advancing Harmful Content Detection in Organizational Research: Integrating Large Language Models with Elo Rating System
• Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples
• Reranking-based Generation for Unbiased Perspective Summarization
• Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints
• User-Guided Force-Directed Graph Layout
• Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation
• Reward Models in Deep Reinforcement Learning: A Survey
• Reward Model Interpretability via Optimal and Pessimal Tokens
• DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization
• GRAM: A Generative Foundation Reward Model for Reward Generalization
• TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
• Value-Free Policy Optimization via Reward Partitioning
• PB²: Preference Space Exploration via Population-Based Methods in Preference-Based Reinforcement Learning
• VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
• Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization
• PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization
• AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models
• Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory
• From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment
• Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization
• Personalized LLM Decoding via Contrasting Personal Preference
• Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization
• From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review
• Rating competitors in games with strength-dependent tie probabilities
• Pareto Optimal Code Generation
• Large Language Models Can Be a Viable Substitute for Expert Political Surveys When a Shock Disrupts Traditional Measurement Approaches
• Debiasing Online Preference Learning via Preference Feature Preservation
• Preference Learning for AI Alignment: a Causal Perspective
• FlexSpeech: Towards Stable, Controllable and Expressive Text-to-Speech
• Reliable Evaluation of MRI Motion Correction: Dataset and Insights
• Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey
• SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs
• Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models
• Search Arena: Analyzing Search-Augmented LLMs
• RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation
• When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration
• Identifying Terms and Conditions Important to Consumers using Crowdsourcing
• QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering
• BPO: Revisiting Preference Modeling in Direct Preference Optimization
• Policy-labeled Preference Learning: Is Preference Enough for RLHF?
• Robust Preference Optimization via Dynamic Target Margins
• Negative-Guided Subject Fidelity Optimization for Zero-Shot Subject-Driven Generation
• RewardAnything: Generalizable Principle-Following Reward Models
• DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
• TO-GATE: Clarifying Questions and Summarizing Responses with Trajectory Optimization for Eliciting Human Preference
• Understanding the Impact of Sampling Quality in Direct Preference Optimization
• Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences
• Beyond the Surface: Measuring Self-Preference in LLM Judgments
• Beyond Text Compression: Evaluating Tokenizers Across Scales
• Quantitative LLM Judges
• What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context
• SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis
• Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment
• Assumption-free stability for ranking problems
• Beyond RLHF: A Unified Theoretical Framework of Alignment
• RewardBench 2: Advancing Reward Model Evaluation
• Doubly Robust Alignment for Large Language Models
• CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries
• K-order Ranking Preference Optimization for Large Language Models
• On Symmetric Losses for Robust Policy Optimization with Noisy Preferences
• Paired comparison models with strength-dependent ties and order effects
• MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning
• Evaluating Gemini in an arena for learning
• InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
• Thompson Sampling in Online RLHF with General Function Approximation
• ChARM: Character-based Act-adaptive Reward Modeling for Advanced Role-Playing Language Agents
• REOrdering Patches Improves Vision Models
• Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
• Learning Parametric Distributions from Samples and Preferences
• Bounded-Abstention Pairwise Learning to Rank
• Discriminative Policy Optimization for Token-Level Reward Models
• Towards Reward Fairness in RLHF: From a Resource Allocation Perspective
• LLM Agents for Bargaining with Utility-based Feedback
• Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
• Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization
• Preference Learning with Response Time: Robust Losses and Guarantees
• Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
• LLMs Judging LLMs: A Simplex Perspective
• Reverse Preference Optimization for Complex Instruction Following
• Photography Perspective Composition: Towards Aesthetic Perspective Recommendation
• Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching
• SquareχPO: Differentially Private and Robust χ²-Preference Optimization in Offline Direct Alignment
• Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
• Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback
• Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
• Risk-aware Direct Preference Optimization under Nested Risk Measure
• Energy-based Preference Optimization for Test-time Adaptation
• Preference Optimization by Estimating the Ratio of the Data Distribution
• Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries
• Learning a Pessimistic Reward Model in RLHF
• FairPO: Robust Preference Optimization for Fair Multi-Label Learning
• Marginal minimization and sup-norm expansions in perturbed optimization
• Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards
• Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
• Frictional Agent Alignment Framework: Slow Down and Don't Break Things
• Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
• SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety
• A Survey on Progress in LLM Alignment from the Perspective of Reward Design
• Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning
• LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
• Incentivizing High-Quality Human Annotations with Golden Questions
• Reward Model Overoptimisation in Iterated RLHF
• Scalable Valuation of Human Feedback through Provably Robust Model Alignment
• Large Language Models Do Multi-Label Classification Differently
• Value-Guided Search for Efficient Chain-of-Thought Reasoning
• On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
• KL-regularization Itself is Differentially Private in Bandits and RLHF
• Shape it Up! Restoring LLM Safety during Finetuning
• MPO: Multilingual Safety Alignment via Reward Gap Optimization
• Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guarantees
• Isotonic Bradley-Terry Model for Paired Comparison Data
• Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
• Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?
• Direct Preference Optimization for Adaptive Concept-based Explanations
• Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge
• A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
• SLMEval: Entropy-Based Calibration for Human-Aligned Evaluation of Large Language Models
• Imitation Learning via Focused Satisficing
• Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search
• Preference Learning with Lie Detectors can Induce Honesty or Evasion
• Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency
• Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks
• Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
• Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization
• Modeling Aesthetic Preferences in 3D Shapes: A Large-Scale Paired Comparison Study Across Object Categories
• Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward
• Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation
• SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment
• Pairwise Calibrated Rewards for Pluralistic Alignment
• Online Iterative Self-Alignment for Radiology Report Generation
• AdaBoN: Adaptive Best-of-N Alignment
• Mutual-Taught for Co-adapting Policy and Reward Models
• J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge
• Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models
• REMOR: Automated Peer Review Generation with LLM Reasoning and Multi-Objective Reinforcement Learning
• A Systematic Analysis of Base Model Choice for Reward Modeling
• SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
• Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment
• WorldPM: Scaling Human Preference Modeling
• Maximum Selection and Sorting with Adversarial Comparators and an Application to Density Estimation
• Distributionally Robust Listwise Preference Optimization
• Bayesian and Motivated Reasoning in AI Agents
• Self-Consuming Generative Models with Adversarially Curated Data
• InfoPO: On Mutual Information Maximization for Large Language Model Alignment
• LCES: Zero-shot Automated Essay Scoring via Pairwise Comparisons Using Large Language Models
• On the Robustness of Reward Models for Language Model Alignment
• Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models
• Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning
• Convert Language Model into a Value-based Strategic Planner
• Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes
• Inducing Robustness in a 2 Dimensional Direct Preference Optimization Paradigm
• Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
• Learning Semantic Priorities for Autonomous Target Search
• Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
• Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation
• The Model Knows Your Project, Not You: Measuring Recognition in LLMs with NameRank
• JudgeArena: A Unified Framework for Reproducible LLM-Judge Evaluation
• War of Words: The Competitive Dynamics of Legislative Processes
• War of Words II: Enriched Models of Law-Making Processes
• JP-TL-Bench: Anchored Pairwise LLM Evaluation for Bidirectional Japanese-English Translation
• Scorio.jl: A Julia package for ranking stochastic responses
• Transposition is Nearly Optimal for IID List Update
• Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models
• Regularization in Paired Comparison Models via Pseudo-Games and Phantom Players
• Configurable Reward Model for Balanced Safety Alignment
• Causal methods for LLM development and evaluation
• Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety
• JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment
• General Preference Reinforcement Learning
• A Hyperbolic Cosine Latent Trait Model For Unfolding Dichotomous Single-Stimulus Responses
• Do Large Language Models Always Tell The Same Stories?
• Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
• Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML
• Sequential Data Poisoning in LLM Post-Training
• Robust AI Evaluation through Maximal Lotteries
• GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
• Calibrating Translation Decoding with Quality Estimation on LLMs
• Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization
• Mitigating Reward Hacking in RLHF via Advantage Sign Robustness
• Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks
• SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling
• A Dual Evaluation for Music Transcription
• Private Direct Preference Optimization for LLM Alignment
• FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables
• Advances in Human-Robot Handshaking
• Quantifying Response Dependence Between Two Dichotomous Items Using the Rasch Model
• Efficient Portfolio Selection through Preference Aggregation with Quicksort and the Bradley--Terry Model
• Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion
• From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning
• CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization
• AdaViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference Optimization
• In-context Ranking Preference Optimization
• Reinforcement Learning from Multi-level and Episodic Human Feedback
• A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents
• Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning
• SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization
• LoRe: Personalizing LLMs via Low-Rank Reward Modeling
• Remedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling
• Energy-Based Reward Models for Robust Language Model Alignment
• SPIE: Semantic and Structural Post-Training of Image Editing Diffusion Models with AI feedback
• ADAPT: Actively Discovering and Adapting to Preferences for any Task
• FiSMiness: A Finite State Machine Based Paradigm for Emotional Support Conversations
• KVAE: Family of Tokenizers for Multimodal Generative Models
• Cautious Context Steering for Language Model Personalization
• GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Papers
• Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation
• MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling
• LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews
• Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
• Discriminator-Free Direct Preference Optimization for Video Diffusion
• Network-based ranking in social systems: three challenges
• FuseRL: Dense Preference Optimization for Heterogeneous Model Fusion
• ThoughtProbe: Classifier-Guided Thought Space Exploration Leveraging LLM Intrinsic Reasoning
• Adversarial Training of Reward Models
• The uncanny valley effect in typically developing children and its absence in children with autism spectrum disorders. [europepmc]
• Scale Separation Reliability: What Does It Mean in the Context of Comparative Judgment? [europepmc]
• A Multidimensional IRT Approach for Dynamically Monitoring Ability Growth in Computerized Practice Environments. [europepmc]
• Tumor heterogeneity and acquired drug resistance in FGFR2-fusion-positive cholangiocarcinoma through rapid research autopsy. [europepmc]
• Geometric Affordance Perception: Leveraging Deep 3D Saliency With the Interaction Tensor. [europepmc]
• Attention-Guided Multi-Scale Feature Fusion Network for Low-Light Image Enhancement. [europepmc]
• Scaling preferences using probabilistic choice models: is there a ratio-scale representation of subjective liking? [europepmc]
• Value Propositions of Public Adult Hearing Rehabilitation in Denmark. [europepmc]
• Pic2Plate: A Vision-Language and Retrieval-Augmented Framework for Personalized Recipe Recommendations. [europepmc]
• Human-anchored longitudinal comparison of generative AI with a bias-calibrated LLM-as-judge. [europepmc]
• Ideometrics: a scientific approach to generating, evaluating, and prioritising ideas. [europepmc]
• Relationship Between Display Pixel Structure and Gloss Perception. [europepmc]