AutoResearch-RL is an RL agent that autonomously conducts perpetual neural architecture and hyperparameter search via code modification without human supervision.
Retrieval-augmented multi-scale framework for county-level crop yield prediction addressing regional and temporal challenges in agricultural forecasting.
Adversarial latent-state training framework for robust policies in partially observable MDPs under latent distribution shift with theoretical guarantees.
ShakyPrepend applies differential privacy-inspired tools to multi-group learning for improved sample complexity and adaptation to group structure.
Analyzes norm-hierarchy transitions explaining when neural networks transition from spurious shortcuts to structured representations during training.
Learning concept bottleneck models from mechanistic explanations instead of pre-specified or LLM-prompted concepts for improved interpretability and predictive power.
Addresses representation entanglement between physiologic signal and institutional artifacts in clinical ML under systematic distribution shift from heterogeneous practices.
Develops tunable-complexity priors for diffusion models and normalizing flows to balance representation error and overfitting in inverse problem solving.
N-Tree Diffusion enables efficient long-horizon wildfire risk forecasting by hierarchically extending diffusion models across multiple prediction steps.
Examines neural scaling laws in sub-20M parameter regime for TinyML/edge AI, showing both ConvNets and MobileNetV2 follow power law error scaling.
Hierarchical multi-agent RL framework for controlling reconfigurable intelligent surfaces in mmWave systems without channel state information estimation overhead.
Accelerates multi-task learning gradient balancing through bi-level optimization to improve MGDA-type methods for handling task conflicts.
Deterministic fuzzy triage system for legal compliance classification using dual encoders and transparent bands, demonstrated on contractual evidence HIPAA/NERC-CIP alignment.
Generalizes linear autoencoder recommender systems by decoupling expected quadratic loss to improve hyperparameter flexibility beyond prior constraints.
DualSpec accelerates LLM-based research agents by speculating on actions during reasoning to reduce latency in long-horizon information-seeking tasks with tool use.
Data Agent uses end-to-end optimization to dynamically select informative samples during training acceleration.
Cost-driven state representation learning for control tasks from high-dimensional partial observations.
Tokenization approach enables transformers to outperform gradient boosting on tabular forecasting tasks.
Diffusion transformer framework generates 3D genome structures conditioned on Hi-C contact maps.
Unified framework for knowledge transfer between models of different sizes, enabling bidirectional scaling.
OCLADS framework for continual learning in IoT anomaly detection under non-stationary data distributions.
Theoretical analysis connecting drifting models and score-based generative models through kernel-weighted discrepancy.
RL framework optimizes cleaning schedules for solar panels using PPO algorithm in arid regions.
Method for transferring knowledge from pre-trained models to different architectural scales using frequency-domain information.
Neural dynamics-informed pre-training framework for personalized brain functional network construction addressing heterogeneous neural activity patterns.
Data-driven approach using dynamic latent space representations for generative prediction of laser-induced rocket ignition with uncertainty quantification.
Obliviator method revealing vulnerability of concept erasure to nonlinear adversaries, analyzing statistical dependencies in representation unlearning.
ECG classification on PTB-XL dataset using simplified CNN-VAE with data-centric approach for cardiovascular disease detection.
Constraints Matrix Diffusion-based generative neural solver for vehicle routing problems emphasizing local optimization and small-scale generalization.
TS-MLLM: multi-modal LLM framework for industrial time-series analysis combining temporal signals, frequency-domain visuals, and textual knowledge for prognostics.
TT-Sparse: neural building block for learning interpretable sparse rule models using differentiable truth tables balancing performance and human-understandable complexity.
Visual representation framework encoding signals as low-rank adaptations to frozen diffusion foundation models for compact storage and reuse.
Helix: evolutionary reinforcement learning system combining LLMs with RL for open-ended scientific problem solving with improved exploration and generalization.
Critical review synthesizing classical numerical methods and machine learning approaches for solving PDEs, examining six fundamental computational challenges.
Theoretical analysis of relationships between surrogate losses and evaluation metrics, addressing metric mismatch between offline validation and online performance.
Primal-dual natural actor-critic algorithm for constrained MDPs with neural network critics and general policy parameterization, enabling high-dimensional continuous control.
Theoretical analysis of greedy sparse learning algorithms examining convergence failure with step-size decay in matching pursuit and boosting methods.
Reverse Distillation framework addressing poor scaling in protein language models by decomposing large model representations using smaller model guidance.
FedShift: distributed adversarial attack on federated graph learning systems with two-stage hide-and-find approach for model poisoning.
GANRA: GPU-accelerated SMT solver combining LLMs and gradient descent for solving quantifier-free nonlinear real arithmetic problems.
MicroCoder-GRPO: improved training approach for code generation models using Group Relative Policy Optimization with conditional truncation masking for handling longer outputs.
ProgAgent: continual reinforcement learning agent using progress-aware reward learning from unlabeled expert videos, addresses catastrophic forgetting in robotic learning with JAX architecture.
arXiv paper investigating loss of plasticity in Vision Transformers for continual learning, examining why attention-based models struggle to adapt to new tasks over time.
Deep learning approach for multi-user MIMO wireless precoding using complex projective space parameterization of neural network outputs.
Temporal-difference reinforcement learning algorithm that incorporates gradients of bootstrapped estimates to improve stability over semi-gradient approaches.
Gradient-free guidance method for diffusion models in Bayesian inverse problems avoiding computationally expensive vector-Jacobian products.
Particle filtering analysis of inference-time aggregation and pruning methods for steering LLMs using process reward models to optimize accuracy-cost tradeoffs.
Decision-theory framework for designing probabilistic weather forecasts tailored to heterogeneous farmer decision-making contexts.
LLM-driven feature engineering pipeline for predicting job execution times in Databricks cloud systems to optimize cost allocation.
Bayesian Transformer framework for probabilistic power grid load forecasting with uncertainty quantification under distributional shifts.