Entities · Locations
cs.LG
70 articles tagged with this entity.
-
FedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation
-
Efficient Bayesian Deep Ensembles via Analytic Predictive Inference
-
When Certificates Fail: A Unified Safety Framework for Embedded Neural Interface Models
-
Can We Really Learn One Representation to Optimize All Rewards?
-
Open-Ended Scenario Reasoning for Specialist Model Adaptation
-
Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies
-
Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data
-
Can Model Merging Improve Aggregation in DiLoCo?
-
Reduced-Order Models: The Mother of World Models
-
One Framework for All: Cross-Modal Membership Inference for Generative Models
-
ManifoldFlow: SPD-Relaxed Stiefel Layers with Learnable Singular Spectrum
-
Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models
-
Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning
-
SABER: A Semantic-Aligned Brain Network Analysis Framework via Multi-scale Hypergraphs
-
$\mu$pscaling small models: Principled warm starts and hyperparameter transfer
-
Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again
-
Calibrating the Evaluator: Does Probability Calibration Mitigate Preference Coupling in LLM Agent Feedback Loops?
-
Geometric Measurements of the Axiom of Choice in Neural Proof Embeddings
-
Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies
-
VISTA-DZ: Visual Semantic Trajectory Adaptation for Personalized Dilemma Zone Prediction
-
Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models
-
SOLAR: AI-Powered Speed-of-Light Performance Analysis
-
Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQA
-
Fast LeWorldModel
-
Sutra: Tensor-Op RNNs as a Compilation Target for Vector Symbolic Architectures
-
RotRNN: Modelling Long Sequences with Rotations
-
Do Thinking Tokens Help with Safety?
-
Contagion Networks: Evaluator Bias Propagation in Multi-Agent LLM Systems
-
Critical Percolation as a Synthetic Data Model for Interpretability
-
INDEQS: Informed Neural controlled Differential EQuationS
-
Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier
-
LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents
-
scGTN: Deep Siamese Graph Transformer Network for Single-cell RNA Sequencing Clustering
-
ReRAM-aware Model Finetuning addressing I-V Non-linearity and Retention Errors
-
Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning
-
LLMs on Tabular Data with Limited Semantics: Evidence from Industrial Car Retrofit Prediction
-
Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data
-
daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization
-
Multiple Descents in Deep Learning as a Sequence of Order-Chaos Transitions in LSTM Networks
-
How Post-Training Shapes Biological Reasoning Models
-
Learning in the Recurrent State: Gradient Descent with Linear Recurrent Networks
-
Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call
-
Best Arm Identification with Minimal Regret
-
Gefen: Optimized Stochastic Optimizer
-
Detecting Functional Memorization in Code Language Models
-
Toward Calibrated, Fair, and accurate Deepfake Detection
-
TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts
-
SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning
-
Conservation Laws from Data Symmetry in Neural Networks
-
Entropy, Disagreement, and the Limits of Foundation Models in Genomics
-
LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks
-
ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs
-
Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting
-
BCG-FM: A Foundation Model for Ambient Cardiac Health Sensing
-
LEAF: Growing Trees Without Branching for Speech-Aware Large Language Model Post-Training
-
Hierarchical Projection for Adaptive Knowledge Transfer
-
TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs
-
Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short
-
Safe-RULE: Safe Reinforcement UnLEarning
-
LAGO: A Local-Global Optimization Framework Combining Trust Region Methods and Bayesian Optimization
-
The Identity Trap in EEG Foundation Models: A Diagnostic Audit
-
Should You Use Your Large Language Model to Explore or Exploit?
-
Endogenous Resistance to Activation Steering in Language Models
-
TorchKM: A GPU-Oriented Library for Kernel Learning and Model Selection
-
Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
-
Limitations of Normalization in Attention Mechanism
-
Generative Models Erode Human Temporal Learning Through Market Selection
-
OffQ: Taming Structured Outliers in LLM Quantization by Offsetting
-
RePo: Language Models with Context Re-Positioning
-
DEFINED: A Data-Efficient Computational Framework for Fine-Grained Creativity Assessment in Debate Scenarios