QD-LLM evolves prompt embeddings via neuroevolution in a quality-diversity framework, delivering 46% higher coverage and 41% higher QD-score than prior methods on coding and writing benchmarks.
Title resolution pending
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
fields
cs.NE 4 cs.RO 4 cs.CV 2 cs.LG 2 quant-ph 2 astro-ph.GA 1 cond-mat.mes-hall 1 cs.AI 1 eess.SP 1years
2026 18representative citing papers
ENMP prunes negative LoRA modules via evolutionary search to boost merging performance to new state-of-the-art levels across language and vision tasks.
Proprioceptive distribution matching adapts simulators for legged robot policies by comparing observation and action distributions, reducing sim-to-real gaps with minimal real data and no external sensing.
GeoPAS represents optimization problems via multi-scale 2D geometric slices fed to a validity-aware CNN that aggregates embeddings for risk-aware solver selection and log-scale performance prediction, outperforming the single best solver on COCO/BBOB benchmarks under multiple evaluation splits.
RGSE adapts text embeddings at test time via evolutionary search, using cosine similarity rewards from high-confidence visual proposals to improve open-vocabulary object detection under distribution shifts.
Global-MPPI integrates kernel SOS global search with MPPI local refinement and graduated non-convexity smoothing to achieve faster convergence and lower costs on high-dimensional contact-rich manipulation tasks.
Introduces a single-number performance measure, file-based benchmarking, and efficient text-file storage to evaluate and compare stopping criteria for EMO algorithms.
CCV-QAOA is a new complex-valued continuous-variable variant of QAOA that solves real and complex multivariate optimization problems via a variational framework.
A flow-matching model derives manipulation strategies from object affordance, adds an adversarial interaction prior, and uses stability simulation to generate natural, effective human-human co-manipulation motions.
A k-nearest-neighbor approach constructs problem-specific algorithm portfolios that outperform both single solvers and the virtual best solver in fixed-budget black-box optimization.
Derives a generalization bound for GP-based symbolic regression that decomposes the gap into structure-selection complexity and constant-fitting complexity under tree constraints.
Microscopic treatment of the hybrid segment in mesoscopic Kitaev chains shows that Andreev bound state parity crossings define optimal sweet spots for localized Majoranas with large gaps.
Differentiable simulation enables torque-sensor-free actuator model identification from trajectory data, achieving 1.88x better position tracking than a stand-trained baseline and 46% longer travel in downstream locomotion policies.
Test-time steering of pre-trained whole-body policies via sample-based planning lets legged robots generalize dynamic loco-manipulation to varied heavy objects and tasks without additional training or tuning.
PhDLspec combines differential spectra from physical stellar models with a transformer to derive approximately 30 stellar parameters from low-resolution spectra hundreds of times faster than traditional calculations.
Data flow space model merging is formalized as a mixed binary-continuous black-box optimization problem, where a structured approach respecting variable dependencies achieves 6.7% higher accuracy and 51.4% smaller search space than unstructured methods on real language models.
D-QEO framework uses quantum topographical preconditioning on separable functions via small parallel subcircuits to generate seeds that accelerate classical global optimization and avoid exponential failure rates.
LoRA pretraining per environment plus weighted aggregation at inference cuts EER by 15% and training time by 83% for open-set RFF authentication under varying channels.
citing papers explorer
-
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
QD-LLM evolves prompt embeddings via neuroevolution in a quality-diversity framework, delivering 46% higher coverage and 41% higher QD-score than prior methods on coding and writing benchmarks.
-
Evolutionary Negative Module Pruning for Better LoRA Merging
ENMP prunes negative LoRA modules via evolutionary search to boost merging performance to new state-of-the-art levels across language and vision tasks.
-
Simulator Adaptation for Sim-to-Real Learning of Legged Locomotion via Proprioceptive Distribution Matching
Proprioceptive distribution matching adapts simulators for legged robot policies by comparing observation and action distributions, reducing sim-to-real gaps with minimal real data and no external sensing.
-
GeoPAS: Geometric Probing for Algorithm Selection in Continuous Black-Box Optimisation
GeoPAS represents optimization problems via multi-scale 2D geometric slices fed to a validity-aware CNN that aggregates embeddings for risk-aware solver selection and log-scale performance prediction, outperforming the single best solver on COCO/BBOB benchmarks under multiple evaluation splits.
-
Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection
RGSE adapts text embeddings at test time via evolutionary search, using cosine similarity rewards from high-confidence visual proposals to improve open-vocabulary object detection under distribution shifts.
-
Global Sampling-Based Trajectory Optimization for Contact-Rich Manipulation via KernelSOS
Global-MPPI integrates kernel SOS global search with MPPI local refinement and graduated non-convexity smoothing to achieve faster convergence and lower costs on high-dimensional contact-rich manipulation tasks.
-
Benchmarking Stopping Criteria for Evolutionary Multi-objective Optimization
Introduces a single-number performance measure, file-based benchmarking, and efficient text-file storage to evaluate and compare stopping criteria for EMO algorithms.
-
A Complex-Valued Continuous-Variable Quantum Approximation Optimization Algorithm (CCV-QAOA)
CCV-QAOA is a new complex-valued continuous-variable variant of QAOA that solves real and complex multivariate optimization problems via a variational framework.
-
Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation
A flow-matching model derives manipulation strategies from object affordance, adds an adversarial interaction prior, and uses stability simulation to generate natural, effective human-human co-manipulation motions.
-
Similarity-based Portfolio Construction for Black-box Optimization
A k-nearest-neighbor approach constructs problem-specific algorithm portfolios that outperform both single solvers and the virtual best solver in fixed-budget black-box optimization.
-
On the Generalization Bounds of Symbolic Regression with Genetic Programming
Derives a generalization bound for GP-based symbolic regression that decomposes the gap into structure-selection complexity and constant-fitting complexity under tree constraints.
-
Optimal Majoranas in Mesoscopic Kitaev Chains
Microscopic treatment of the hybrid segment in mesoscopic Kitaev chains shows that Andreev bound state parity crossings define optimal sweet spots for localized Majoranas with large gaps.
-
Trajectory-based actuator identification via differentiable simulation
Differentiable simulation enables torque-sensor-free actuator model identification from trajectory data, achieving 1.88x better position tracking than a stand-trained baseline and 46% longer travel in downstream locomotion policies.
-
Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation
Test-time steering of pre-trained whole-body policies via sample-based planning lets legged robots generalize dynamic loco-manipulation to varied heavy objects and tasks without additional training or tuning.
-
PhDLspec: physical-prior embedded deep learning method for spectroscopic determination of stellar labels in high-dimensional parameter space
PhDLspec combines differential spectra from physical stellar models with a transformer to derive approximately 30 stellar parameters from low-resolution spectra hundreds of times faster than traditional calculations.
-
Black-Box Optimization of Mixed Binary-Continuous Variables: Challenges and Opportunities in Evolutionary Model Merging
Data flow space model merging is formalized as a mixed binary-continuous black-box optimization problem, where a structured approach respecting variable dependencies achieves 6.7% higher accuracy and 51.4% smaller search space than unstructured methods on real language models.
-
Distributed Quantum-Enhanced Optimization: A Topographical Preconditioning Approach for High-Dimensional Search
D-QEO framework uses quantum topographical preconditioning on separable functions via small parallel subcircuits to generate seeds that accelerate classical global optimization and avoid exponential failure rates.
-
Rapid LoRA Aggregation for Wireless Channel Adaptation in Open-Set Radio Frequency Fingerprinting
LoRA pretraining per environment plus weighted aggregation at inference cuts EER by 15% and training time by 83% for open-set RFF authentication under varying channels.