3/31/2026
LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesis
Uses LLMs to programmatically synthesize anomaly detectors for tabular data without direct processing of raw data for privacy.
3/31/2026
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
ACE framework evolves context for self-improving LLM agents, addressing brevity bias and context collapse in iterative refinement.
3/31/2026
Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
Mitigates premature exploitation in particle filtering for inference-time scaling of language models using process reward models.
3/31/2026
TabPFN-Wide: Continued Pre-Training for Extreme Feature Counts
TabPFN-Wide extends prior-data fitted networks for tabular data with extreme feature counts in biomedicine applications.
3/31/2026
Constraints-of-Thought: A Framework for Constrained Reasoning in Language-Model-Guided Search
Constraints-of-Thought framework enables LLMs to perform constrained multi-step reasoning while satisfying symbolic constraints and user intent.
3/31/2026
PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling
PANTHER applies generative pretraining to model user behavior sequences beyond language, using multi-dimensional action attributes.
3/31/2026
Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards
Bandit algorithm for high-stakes sequential decision-making that learns when to abstain from actions with irreparable consequences.
3/31/2026
Dense and Diverse Goal Coverage in Multi Goal Reinforcement Learning
RL algorithm for learning policies that maximize return while inducing dispersed state distributions across multiple reward sources.
3/31/2026
Decomposable Neuro Symbolic Regression
Transformer-based symbolic regression method for discovering interpretable mathematical expressions from observed data.
3/31/2026
From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training
Two-stage entropy approach for noise-tolerant multimodal LLM training using reinforcement learning with verifiable rewards.
3/31/2026
Object-Centric World Models for Causality-Aware Reinforcement Learning
Object-centric world models for reinforcement learning using decomposed representations to improve sample efficiency in multi-object environments.
3/31/2026
UniGame: Turning a Unified Multimodal Model Into Its Own Adversary
UniGame addresses inconsistency in unified multimodal models between understanding and generation through adversarial framework.
3/31/2026
Single-Round Scalable Analytic Federated Learning
SAFLe framework enabling scalable non-linear federated learning in a single round with heterogeneous data distribution invariance.
3/31/2026
Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval
Domain adaptive retrieval using prototype-based semantic consistency alignment to transfer knowledge from labeled to unlabeled domains.
3/31/2026
Measuring all the noises of LLM Evals
Research on measuring noise in LLM evaluations using statistical methods to separate signal from noise in prediction, data, and combined noise.
3/31/2026
Electricity Price Forecasting: Bridging Linear Models, Neural Networks and Online Learning
Day-ahead electricity price forecasting combining linear models, neural networks and online learning for volatile market prediction.
3/31/2026
Symbolic Regression for Shared Expressions: Introducing Partial Parameter Sharing
Symbolic regression with partial parameter sharing for discovering expressions describing related phenomena with varying parameters.
3/31/2026
Hellinger Multimodal Variational Autoencoders
Hellinger multimodal VAEs using probabilistic opinion pooling to aggregate unimodal inference distributions.
3/31/2026
Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
Sparse-RL addresses memory bottleneck in LLM reinforcement learning by reducing KV cache overhead during long-horizon rollouts.
3/31/2026
Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting
Dual-prototype disentanglement framework for context-aware time series forecasting using dynamic temporal pattern learning.
3/31/2026
A Dynamic Framework for Grid Adaptation in Kolmogorov-Arnold Networks
Generalized framework for adaptive grid allocation in Kolmogorov-Arnold Networks accounting for target function complexity.
3/31/2026
Smoothing the Score Function for Generalization in Diffusion Models: An Optimization-based Explanation Framework
Theoretical framework explaining memorization in diffusion models through weighted sum of empirical score functions.
3/31/2026
TextBFGS: A Case-Based Reasoning Approach to Code Optimization via Error-Operator Retrieval
TextBFGS applies case-based reasoning to iterative code generation with LLMs, using past solutions to guide optimization.
3/31/2026
Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking
Benchmarks Echo State Networks for univariate time series forecasting against traditional statistical methods on M4 dataset.
3/31/2026
DADP: Domain Adaptive Diffusion Policy
Domain adaptive diffusion policy for control that generalizes to unseen transition dynamics through domain representation learning.
3/31/2026
Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
Analyzes GRPO limitations in exploration and difficulty adaptation for LLM reasoning, proposing improvements to advantage symmetry.
3/31/2026
Joint Embedding Variational Bayes
VJE framework for self-supervised learning using reconstruction-free latent variables with symmetric conditional ELBO optimization.
3/31/2026
Live Knowledge Tracing: Real-Time Adaptation using Tabular Foundation Models
Applies tabular foundation models to knowledge tracing for real-time student learning prediction without extensive offline training.
3/31/2026
Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification
Interpretable image classification using hierarchical concept embeddings recovered from vision-language models.
3/31/2026
$\phi$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models
φ-DPO addresses fairness in continual learning for multimodal models when training data is imbalanced across tasks.
3/31/2026
Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection
Reduces transformer KV cache by using low-dimensional keys for attention selection while maintaining full-dimensional values.
3/31/2026
Distributional Regression with Tabular Foundation Models: Evaluating Probabilistic Predictions via Proper Scoring Rules
Proposes using proper scoring rules to evaluate probabilistic predictions from tabular foundation models instead of point-estimate metrics.
3/31/2026
Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers
Replaces dense attention projections with Walsh Hadamard Transforms to reduce transformer parameters by 25% while maintaining performance.
3/31/2026
CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad
LLM agent framework with causal scratchpad for open-ended scientific discovery through iterative program evolution.
3/31/2026
Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
Theoretical analysis of dataset distillation for encoding low-dimensional task representations from gradient-based learning.
3/31/2026
Off-Policy Learning with Limited Supply
Off-policy learning framework for contextual bandits with constrained item supply in recommendation and advertising.
3/31/2026
Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed Graphs
Backdoor attack method on text-attributed graphs by injecting malicious cues into node text.
3/31/2026
Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration
RL approach decoupling exploration and policy optimization using uncertainty-guided tree search for hard exploration problems.
3/31/2026
Scaling Attention via Feature Sparsity
Sparse Feature Attention (SFA) method reducing transformer attention complexity via feature-level sparsity for ultra-long contexts.
3/31/2026
Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits
Analysis of systematic biases in Chinchilla Approach 2 neural scaling law fits for compute-optimal LLM allocation.
3/31/2026
SkillRouter: Skill Routing for LLM Agents at Scale
Skill routing system for LLM agents managing and selecting from large skill ecosystems at inference time.
3/31/2026
Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG
Synthetic Mixed Training method combining synthetic QAs and documents to scale LLM knowledge acquisition beyond RAG limitations.
3/31/2026
Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch
Study comparing LLM agents against classical hyperparameter optimization algorithms using autoresearch framework for hyperparameter tuning.
3/31/2026
PEANUT: Perturbations by Eigenvector Alignment for Attacking Graph Neural Networks Under Topology-Driven Message Passing
Attack method (PEANUT) exploiting GNN vulnerabilities through graph topology perturbations in message passing.
3/31/2026
Shapley meets Rawls: an integrated framework for measuring and explaining unfairness
Framework using Shapley values to measure and explain unfairness in ML models under group fairness criteria.
3/31/2026
Evasion Adversarial Attacks Remain Impractical Against ML-based Network Intrusion Detection Systems, Especially Dynamic Ones
Study on adversarial evasion attacks against ML-based network intrusion detection systems, showing attacks remain impractical against dynamic systems.
3/31/2026
LSM-GNN: Large-scale Storage-based Multi-GPU GNN Training by Optimizing Data Transfer Scheme
Multi-GPU GNN training system optimizing data transfer for large-scale graphs exceeding GPU memory capacity via storage-based approaches.
3/31/2026
Predictive variational inference: Learn the predictively optimal posterior distribution
Framework for variational inference that optimizes posterior distributions under model misspecification for better predictive accuracy.
3/31/2026
Trans-Glasso: A Transfer Learning Approach to Precision Matrix Estimation
Transfer learning method for precision matrix estimation leveraging related source data with limited target samples.
3/31/2026
Mean--Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical Study
RL approach for continuous-time portfolio selection using unknown diffusion processes, with data-driven strategy learning.