2/27/2026
Procedural Fairness in Machine Learning
Defines and formalizes procedural fairness in machine learning models drawing from philosophy and psychology, addressing fairness beyond distributive metrics.
2/27/2026
Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
Analyzes parameter-efficient fine-tuning for continual learning using Neural Tangent Kernel theory to understand model adaptation and catastrophic forgetting mitigation.
2/27/2026
Efficient Graph Coloring with Neural Networks: A Physics-Inspired Approach for Large Graphs
Physics-inspired neural framework using graph neural networks to solve large-scale graph coloring combinatorial optimization problems near algorithmic phase transitions.
2/27/2026
Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure
Proposes label unlearning method for vertical federated learning using representation-level manifold mixup to enable privacy-preserving model unlearning.
2/27/2026
Beyond Attribution: Unified Concept-Level Explanations
Model-agnostic explanation technique integrating concept-based approaches with diverse explanation forms beyond attribution methods.
2/27/2026
Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
Reinforcement learning framework for aligning few-step diffusion models with downstream objectives using stepwise policy optimization.
2/27/2026
Neuro-Symbolic AI for Analytical Solutions of Differential Equations
Neuro-symbolic framework automating discovery of analytical solutions to differential equations using formal grammars and continuous search.
2/27/2026
Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits
Theoretical analysis of sample complexity for offline reinforcement learning with f-divergence regularization in contextual bandits.
2/27/2026
Mixing It Up: Exploring Mixer Networks for Irregular Multivariate Time Series Forecasting
Evaluation of MLP-Mixer architectures for forecasting irregular multivariate time series with missing values.
2/27/2026
Using the Path of Least Resistance to Explain Deep Networks
Alternative to Integrated Gradients for neural network interpretability using model-induced metrics instead of straight attribution paths.
2/27/2026
Global graph features unveiled by unsupervised geometric deep learning
Unsupervised geometric deep learning framework for capturing local and global graph structure using hourglass autoencoder.
2/27/2026
Sample Compression for Self Certified Continual Learning
Continual learning method using sample compression theory to provide computable guarantees while avoiding catastrophic forgetting.
2/27/2026
Extensions of the regret-minimization algorithm for optimal design
Extension of regret minimization algorithms for optimal experimental design and active learning sample selection.
2/27/2026
RaPA: Enhancing Transferable Targeted Attacks via Random Parameter Pruning
Method for improving transferable adversarial attacks via random parameter pruning to reduce reliance on small parameter subsets.
2/27/2026
Large Language Model Compression with Global Rank and Sparsity Optimization
Compression technique for large language models using global rank and sparsity optimization with layer-wise weight allocation.
2/27/2026
Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting
Framework for uncertainty quantification with corrupted or missing labels using conformal prediction with robust re-weighting.
2/27/2026
FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization
Large-scale benchmark for evaluating machine learning solvers on combinatorial optimization using real-world industrial datasets.
2/27/2026
The Spacetime of Diffusion Models: An Information Geometry Perspective
Information geometry perspective on diffusion model latent spaces, analyzing deterministic and stochastic decoders.
2/27/2026
On the Lipschitz Continuity of Set Aggregation Functions and Neural Networks for Sets
Theoretical analysis of Lipschitz continuity properties for neural networks operating on set-structured data.
2/27/2026
RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?
Research on whether language models can learn to evade latent-space safety monitors, with implications for LLM alignment and security.
2/27/2026
Learning Task-Agnostic Motifs to Capture the Continuous Nature of Animal Behavior
Framework for discovering continuous motor motifs in animal behavior using latent basis functions instead of discrete syllables.
2/27/2026
Skewed Score: A statistical framework to assess autograders
Statistical framework for evaluating LLM-as-a-judge systems, addressing reliability and bias issues in automated LLM output evaluation.
2/27/2026
Fast and Flexible Probabilistic Forecasting of Dynamical Systems using Flow Matching and Physical Perturbation
Flow matching approach for probabilistic forecasting of dynamical systems using physical perturbations instead of standard Gaussian perturbations.
2/27/2026
Zero-Variance Gradients for Variational Autoencoders
Silent Gradients approach for training VAEs by restricting decoder architecture to reduce gradient estimation variance.
2/27/2026
Online time series prediction using feature adjustment
Online time series forecasting method using feature adjustment to handle distribution shift in sequential data deployment.
2/27/2026
Random Matrix Theory-guided sparse PCA for single-cell RNA-seq data
Sparse PCA method using random matrix theory for dimensionality reduction in noisy single-cell RNA-seq data.
2/27/2026
Predicting LLM Reasoning Performance with Small Proxy Model
rBridge framework enabling small proxy models (≤1B params) to predict reasoning performance of larger LLMs, optimizing dataset scaling.
2/27/2026
Information-Theoretic Bayesian Optimization for Bilevel Optimization Problems
Bayesian optimization method for bilevel optimization problems with expensive black-box functions at both levels.
2/27/2026
Statistical Advantage of Softmax Attention: Insights from Single-Location Regression
Theoretical analysis of softmax attention mechanisms in LLMs through single-location regression task, addressing why softmax dominates alternative activation functions.
2/27/2026
Compute-Optimal Quantization-Aware Training
Study of compute-optimal allocation between full-precision and quantization-aware training phases for neural networks.
2/27/2026
Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
Dynamic safety monitoring system for LLMs that adaptively adjusts computation based on input difficulty.
2/27/2026
Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
Method for improving masked diffusion models by learning better unmasking policies beyond rule-based position scheduling.
2/27/2026
Learning to Answer from Correct Demonstrations
Imitation learning approach for training models with multiple acceptable answers from limited correct demonstrations.
2/27/2026
Simplex-to-Euclidean Bijections for Categorical Flow Matching
Method for learning probability distributions on simplexes via smooth bijections and Aitchison geometry.
2/27/2026
UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs
UniQL framework combining quantization and low-rank compression with adaptive on-device pruning for edge LLM deployment.
2/27/2026
Sparse Attention Post-Training for Mechanistic Interpretability
Post-training method achieving 99.6% attention sparsity without performance loss for mechanistic interpretability research.
2/27/2026
WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks
WebGym: largest open-source environment with 300k tasks for training visual web agents on realistic websites.
2/27/2026
A Confidence-Variance Theory for Pseudo-Label Selection in Semi-Supervised Learning
Confidence-Variance theory framework for improved pseudo-label selection in semi-supervised learning beyond fixed thresholds.
2/27/2026
Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction between Feature Alignment and Target Fitting
Method for optimizing interaction between feature alignment and target fitting in cross-modal model fine-tuning.
2/27/2026
Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics
Framework for learning Hamiltonian flow maps to enable stable large-timestep molecular dynamics simulations.
2/27/2026
Beyond Fixed Rounds: Data-Free Early Stopping for Practical Federated Learning
Data-free early stopping framework for federated learning using task vector growth rate monitoring.
2/27/2026
Agentic Framework for Epidemiological Modeling
EPIAGENT agentic framework that automatically synthesizes and calibrates epidemiological simulators via iterative program synthesis.
2/27/2026
A Minimum Variance Path Principle for Accurate and Stable Score-Based Density Ratio Estimation
Framework for score-based density ratio estimation addressing path-variance issues in practical training objectives.
2/27/2026
Phase Transitions for Feature Learning in Neural Networks
Theoretical analysis of phase transitions in neural network feature learning on multi-index models.
2/27/2026
Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty Quantification
Technique to detect misbehaviors and hallucinations in large vision-language models using evidential uncertainty quantification.
2/27/2026
Learning Credal Ensembles via Distributionally Robust Optimization
Method for training ensemble models that quantify epistemic uncertainty via distributionally robust optimization.
2/27/2026
When Less is More: The LLM Scaling Paradox in Context Compression
Study of LLM scaling paradox showing larger compressor models can reduce context reconstruction faithfulness despite lower training loss.
2/27/2026
Versor: A Geometric Sequence Architecture
Novel sequence architecture using Conformal Geometric Algebra instead of linear operations for improved generalization and interpretability.
2/27/2026
Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
On-policy distillation method that aligns student models with teacher logit distributions, theoretically framed as KL-constrained RL with reward extrapolation.
2/27/2026
\"UberWeb: Insights from Multilingual Curation for a 20-Trillion-Token Dataset
Analysis of multilingual data curation across 13 languages for 20-trillion-token dataset, addressing multilinguality challenges in foundation models.