Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
hub Mixed citations
The vendi score: A diversity evaluation metric for machine learning
Mixed citation behavior. Most common role is background (40%).
18
Pith papers citing it
Background
40% of classified citations
hub tools
citation-role summary
background 3
dataset 2
citation-polarity summary
representative citing papers
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
STRIDE boosts diversity in one-step diffusion models by injecting PCA-aligned pink noise into transformer features while preserving text alignment and quality.
Spectra defines and controls effective capacity in graph embeddings via the Shannon effective rank of a trace-normalized kernel spectrum, making capacity a post-fit property rather than a pre-training hyperparameter.
Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
PF-MA is a new active learning rule that favors likely-positive uncertain samples to speed up discovery of rare categories in imbalanced visual retrieval.
Differentiable nonconformity scores induce flows that sample conformal prediction set boundaries, and mixing flows across levels produces conformal predictive distributions whose quantiles match the sets.
Noise optimization during sampling recovers diversity in mode-collapsed diffusion models while preserving output fidelity.
SynAE is a multi-metric framework that evaluates how well synthetic benchmarks replicate real data characteristics for multi-turn tool-calling agent testing.
Analogical reasoning increases LLM solution diversity by 90-173% and novelty rate to over 50%, delivering up to 13-fold gains on biomedical tasks including perturbation prediction and cell communication.
Vocabulary dropout prevents diversity collapse in LLM co-evolution by masking proposer logits, yielding average +4.4 point solver gains on mathematical reasoning benchmarks at 8B scale.
Voyager iteratively optimizes a determinantal point process diversity measure to generate synthetic LLM datasets, delivering 1.5-3 times higher diversity than baselines in experiments.
DOLLAR combines variational score and consistency distillation for few-step video generation plus latent reward optimization, reporting 82.57 VBench score and up to 278x speedup over the teacher diffusion model for 128-frame 10-second videos.
Closed-loop multi-LLM systems exhibit robust semantic collapse across model families and interventions, consistent with intrinsic properties of autoregressive generation.
Mid-training LLMs on self-generated diverse reasoning paths improves subsequent RL performance on mathematical benchmarks and OOD tasks.
A diversity-aware selection framework builds materials datasets that improve prediction performance on both targeted (up to 25% gain) and untargeted properties (up to 10% gain) compared to random or non-diverse sampling in noisy experimental settings.
Residual-stream noise injection raises narrative diversity in Arabic educational stories while preserving reading-grade level, outperforming high-temperature sampling across five 7-9B models.
Introduces polychromic objectives adapted into PPO via vine sampling and modified advantages, showing higher success rates and better coverage under perturbations on BabyAI, Minigrid, and algorithmic tasks.
citing papers explorer
-
What Do Evolutionary Coding Agents Evolve?
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
-
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
-
STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models
STRIDE boosts diversity in one-step diffusion models by injecting PCA-aligned pink noise into transformer features while preserving text alignment and quality.
-
Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models
Spectra defines and controls effective capacity in graph embeddings via the Shannon effective rank of a trace-normalized kernel spectrum, making capacity a post-fit property rather than a pre-training hyperparameter.
-
Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
-
Positive-First Most Ambiguous: A Simple Active Learning Criterion for Interactive Retrieval of Rare Categories
PF-MA is a new active learning rule that favors likely-positive uncertain samples to speed up discovery of rare categories in imbalanced visual retrieval.
-
Flow-Based Conformal Predictive Distributions
Differentiable nonconformity scores induce flows that sample conformal prediction set boundaries, and mixing flows across levels produces conformal predictive distributions whose quantiles match the sets.
-
It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models
Noise optimization during sampling recovers diversity in mode-collapsed diffusion models while preserving output fidelity.
-
SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations
SynAE is a multi-metric framework that evaluates how well synthetic benchmarks replicate real data characteristics for multi-turn tool-calling agent testing.
-
Unlocking LLM Creativity in Science through Analogical Reasoning
Analogical reasoning increases LLM solution diversity by 90-173% and novelty rate to over 50%, delivering up to 13-fold gains on biomedical tasks including perturbation prediction and cell communication.
-
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
Vocabulary dropout prevents diversity collapse in LLM co-evolution by masking proposer logits, yielding average +4.4 point solver gains on mathematical reasoning benchmarks at 8B scale.
-
VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs
Voyager iteratively optimizes a determinantal point process diversity measure to generate synthetic LLM datasets, delivering 1.5-3 times higher diversity than baselines in experiments.
-
DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization
DOLLAR combines variational score and consistency distillation for few-step video generation plus latent reward optimization, reporting 82.57 VBench score and up to 278x speedup over the teacher diffusion model for 128-frame 10-second videos.
-
Multi-LLM Systems Exhibit Robust Semantic Collapse
Closed-loop multi-LLM systems exhibit robust semantic collapse across model families and interventions, consistent with intrinsic properties of autoregressive generation.
-
Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
Mid-training LLMs on self-generated diverse reasoning paths improves subsequent RL performance on mathematical benchmarks and OOD tasks.
-
Building informative materials datasets beyond targeted objectives
A diversity-aware selection framework builds materials datasets that improve prediction performance on both targeted (up to 25% gain) and untargeted properties (up to 10% gain) compared to random or non-diverse sampling in noisy experimental settings.
-
Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation
Residual-stream noise injection raises narrative diversity in Arabic educational stories while preserving reading-grade level, outperforming high-temperature sampling across five 7-9B models.
-
Polychromic Objectives for Reinforcement Learning
Introduces polychromic objectives adapted into PPO via vine sampling and modified advantages, showing higher success rates and better coverage under perturbations on BabyAI, Minigrid, and algorithmic tasks.