3/11/2026
You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases
Study of subliminal learning where student LLMs acquire behavioral traits from teacher models via synthetic data training on unrelated domains.
3/11/2026
What Do We Care About in Bandits with Noncompliance? BRACE: Bandits with Recommendations, Abstention, and Certified Effects
BRACE framework for bandits with noncompliance addressing objective selection between recommendation welfare and treatment learning.
3/11/2026
SCDP: Learning Humanoid Locomotion from Partial Observations via Mixed-Observation Distillation
SCDP: sensor-conditioned diffusion policies for humanoid locomotion using only onboard sensors without privileged state estimation.
3/11/2026
Multi-DNN Inference of Sparse Models on Edge SoCs
Multi-DNN inference system for edge devices supporting sparse model variants across heterogeneous processors with improved resource matching.
3/11/2026
Evolution of Photonic Quantum Machine Learning under Noise
Study of photonic quantum machine learning under noise, exploring integration of quantum computing with ML for scalable quantum information processing.
3/11/2026
EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages
EsoLang-Bench: benchmark using esoteric programming languages to evaluate genuine reasoning in LLMs beyond memorization on code tasks.
3/11/2026
From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understanding
C2FMAE: coarse-to-fine masked autoencoder for self-supervised visual pre-training combining global semantics with fine-grained detail.
3/11/2026
Think Before You Lie: How Reasoning Improves Honesty
Study on how reasoning affects honesty in LLMs using moral trade-off dataset, finding reasoning increases rather than decreases honesty.
3/11/2026
A Survey on Decentralized Federated Learning
Survey on decentralized federated learning removing central coordinator and using peer-to-peer coordination for collaborative training.
3/11/2026
Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets
Study of structured lottery tickets in over-parameterized CNNs, connecting pruning to strong lottery ticket hypothesis for computational efficiency.
3/11/2026
Sparse Variational Student-t Processes for Heavy-tailed Modeling
Sparse Variational Student-t Processes framework extending Gaussian processes for scalable heavy-tailed data modeling.
3/11/2026
HYGENE: A Diffusion-based Hypergraph Generation Method
HYGENE: diffusion-based generative model for creating realistic hypergraphs used in social networks, bioinformatics, and recommender systems.
3/11/2026
Robust Training of Neural Networks at Arbitrary Precision and Sparsity
Research on robust neural network training at arbitrary precision and sparsity, addressing gradient flow issues in quantization and sparse regimes.
3/11/2026
ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning
ARLBench benchmark for hyperparameter optimization in reinforcement learning agents, addressing evaluation costs and generalizability across domains and algorithms.
3/11/2026
Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning
Scalable graph neural networks replacing attention with message passing in transformer blocks for large graphs.
3/11/2026
Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
Improved RL training method for LLM reasoning handling all-negative sample groups in GRPO framework.
3/11/2026
JULI: Jailbreak Large Language Models by Self-Introspection
Jailbreak attack on safety-aligned LLMs via self-introspection without requiring model weight access.
3/11/2026
A Systematic Evaluation of On-Device LLMs: Quantization, Performance, and Resources
Systematic evaluation of quantized LLMs on edge devices, testing models 0.5B-14B with seven PTQ methods.
3/11/2026
SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
RL framework using SAT problems to improve LLM reasoning with automatic verification and scalable training.
3/11/2026
FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization
Large-scale benchmark evaluating ML solvers on combinatorial optimization with real-world industrial datasets.
3/11/2026
Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score
Semi-supervised extension of conformal prediction using unlabeled data for uncertainty quantification.
3/11/2026
Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment
Meta-learning approach to rate time series data quality using LLM judgments across diverse domains.
3/11/2026
Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness
Framework addressing multivariate time series challenges: channel dependencies, asynchronous sampling, and missing values.
3/11/2026
Langevin Flows for Modeling Neural Latent Dynamics
Neural latent dynamics model using Langevin equations with VAE framework for capturing spiking activity patterns.
3/11/2026
Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies
MLES: Multimodal LLM-assisted evolutionary search discovers interpretable programmatic control policies for reinforcement learning.
3/11/2026
CTRL Your Shift: Clustered Transfer Residual Learning for Many Small Datasets
CTRL: Clustered Transfer Residual Learning for multi-source ML datasets maintaining per-source reliability and differences.
3/11/2026
RF-Informed Graph Neural Networks for Accurate and Data-Efficient Circuit Performance Prediction
Graph neural networks informed by RF physics principles for accurate, data-efficient prediction of circuit performance.
3/11/2026
Iterative In-Context Learning to Enhance LLMs Abstract Reasoning: The Case-Study of Algebraic Tasks
Iterative in-context learning strategy improves LLM generalization on algebraic reasoning tasks and out-of-distribution examples.
3/11/2026
Kuramoto Orientation Diffusion Models
Score-based generative model using Kuramoto dynamics on periodic domains for orientation-rich image generation.
3/11/2026
ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse
Test-time entropy minimization method using asymmetric learning to adapt models to novel environments without logit inflation.
3/11/2026
REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
Shows expert pruning outperforms merging for compressing sparse mixture-of-experts models on generative tasks.
3/11/2026
Bradley-Terry Policy Optimization for Generative Preference Modeling
Bradley-Terry policy optimization for extending RL-based training to non-verifiable tasks with only pairwise human preference supervision.
3/11/2026
Reinforcing Numerical Reasoning in LLMs for Tabular Prediction via Structural Priors
Reinforcement learning framework combining permutation relative policy optimization to improve LLM reasoning on tabular prediction tasks.
3/11/2026
GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation
Domain-incremental learning framework for graph models that preserves knowledge across multiple graph domains.
3/11/2026
Structured Matrix Scaling for Multi-Class Calibration
Post-hoc calibration method using structured matrix scaling for improving probability estimates in multi-class classifiers.
3/11/2026
Lightweight Time Series Data Valuation on Time Series Foundation Models via In-Context Finetuning
Lightweight data valuation method for time-series foundation models using in-context learning instead of expensive influence functions.
3/11/2026
TSFM in-context learning for time-series classification of bearing-health status
Uses time-series foundation models with in-context learning for bearing-health classification without fine-tuning.
3/11/2026
Periodic Asynchrony: An On-Policy Approach for Accelerating LLM Reinforcement Learning
Proposes periodic asynchrony to separate inference and training deployment for faster LLM reinforcement learning post-training efficiency.
3/11/2026
SA$^{2}$GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation
Graph foundation model framework with structure-aware augmentation for improved robustness against adversarial attacks and domain noise.
3/11/2026
Directional Textual Inversion for Personalized Text-to-Image Generation
Improves textual inversion for personalized text-to-image generation by addressing embedding norm inflation issues in CLIP.
3/11/2026
The Affine Divergence: Aligning Activation Updates Beyond Normalisation
Proposes affine divergence method to align activation updates during gradient descent optimization in neural networks.
3/11/2026
Automating Forecasting Question Generation and Resolution for AI Evaluation
Automates generation and resolution of diverse forecasting questions for evaluating AI systems' general intelligence capabilities.
3/11/2026
Rewards as Labels: Revisiting RLVR from a Classification Perspective
Identifies gradient issues in RLVR methods like GRPO used for LLM reasoning tasks, proposing improvements to reward-based supervision.
3/11/2026
Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions
Framework using influence functions to edit training data and induce targeted model behavior changes for data poisoning robustness evaluation.
3/11/2026
B-DENSE: Branching For Dense Ensemble Network Supervision Efficiency
Diffusion model distillation technique using branching ensemble networks with dense supervision for accelerated sampling.
3/11/2026
MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching
Flow-matching generative model for predicting periodic molecular crystal structures handling large molecules and complex interactions.
3/11/2026
Continual uncertainty learning
Deep reinforcement learning approach for robust control under multiple uncertainties combining domain randomization and uncertainty learning.
3/11/2026
Breaking the Factorization Barrier in Diffusion Language Models
Addresses factorization barrier in diffusion language models through architectural changes enabling efficient parallel token generation.
3/11/2026
Detecting Transportation Mode Using Dense Smartphone GPS Trajectories and Transformer Models
Transformer-based model (SpeedTransformer) for transportation mode detection from smartphone GPS trajectories outperforming LSTM.
3/11/2026
DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmasking
Framework (DUEL) for computing exact likelihood in masked diffusion models by addressing test-time distribution mismatch in ELBO.