2/24/2026
Bootstrapping Task Spaces for Self-Improvement
Presents Exploratory Iteration (ExIt), RL methods enabling agents to self-improve through iterative refinement without fixed iteration limits.
2/24/2026
Select, then Balance: Exploring Exogenous Variable Modeling of Spatio-Temporal Forecasting
Explores exogenous variable modeling in spatio-temporal forecasting systems to improve prediction accuracy.
2/24/2026
Sequential Data Augmentation for Generative Recommendation
Data augmentation strategies for generative recommendation systems improving generalization in sequential user behavior prediction.
2/24/2026
Towards Privacy-Aware Bayesian Networks: A Credal Approach
Privacy-aware Bayesian network approach using credal sets for secure public release of probabilistic graphical models.
2/24/2026
Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration
Multi-agent RL with curiosity-driven exploration using contextual calibration to distinguish novelty from environmental stochasticity.
2/24/2026
DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models
DriftLite: Training-free particle-based approach for inference-time diffusion model adaptation to new distributions.
2/24/2026
Lightweight error mitigation strategies for post-training N:M activation sparsity in LLMs
Error mitigation methods for post-training N:M activation sparsity in LLMs enabling dynamic input-adaptive compression.
2/24/2026
Aurora: Towards Universal Generative Multimodal Time Series Forecasting
Aurora: Multimodal foundation model for cross-domain time series forecasting integrating text and temporal data.
2/24/2026
SpinGPT: A Large-Language-Model Approach to Playing Poker Correctly
SpinGPT applies LLM approach to poker strategy, addressing CFR computational limits in multi-player game settings.
2/24/2026
Effective Quantization of Muon Optimizer States
8-bit blockwise quantization of Muon optimizer states reducing memory overhead for large-scale LLM pretraining.
2/24/2026
Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
Framework for standardizing evaluation of positive-unlabeled learning algorithms under consistent experimental settings.
2/24/2026
STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting
Weather forecasting method using adaptive boundary alignment for regional and global predictions with spatial-temporal modeling.
2/24/2026
Polychromic Objectives for Reinforcement Learning
Polychromic objectives for RL fine-tuning preventing policy collapse and preserving diversity in pretrained model behaviors.
2/24/2026
Diffusion Alignment as Variational Expectation-Maximization
Diffusion Alignment as Variational EM framework addressing reward over-optimization and mode collapse in diffusion model alignment.
2/24/2026
On Predictability of Reinforcement Learning Dynamics for Large Language Models
Analysis of RL-induced parameter dynamics in LLMs revealing rank-1 dominance in reasoning improvements and predictability of training trajectories.
2/24/2026
The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM
Surrogate-free ADMM method for LLM pruning achieving >50% sparsity without accuracy degradation, breaking through conventional compression limits.
2/24/2026
Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model Pretraining
Scaling law formalization incorporating data quality parameter for language model pretraining, extending traditional model/dataset size relationships.
2/24/2026
KVComm: Enabling Efficient LLM Communication through Selective KV Sharing
KVComm: Communication framework for multi-agent LLM systems using selective key-value sharing instead of natural language or hidden states.
2/24/2026
Cost Efficient Fairness Audit Under Partial Feedback
Fairness auditing framework for classifiers with partial feedback using cost-aware data acquisition strategies.
2/24/2026
TROLL: Trust Regions improve Reinforcement Learning for Large Language Models
TROLL: Trust region-based RL method improving upon PPO clipping for LLM fine-tuning, achieving more stable and optimal reward-based training.
2/24/2026
Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
Novel RL algorithm for diffusion LLMs using distribution matching policy optimization to improve reasoning capabilities and match autoregressive LLM performance.
2/24/2026
Medical Interpretability and Knowledge Maps of Large Language Models
Systematic interpretability study of five LLMs' medical knowledge using activation analysis and layer lesioning techniques.
2/24/2026
CleverCatch: A Knowledge-Guided Weak Supervision Model for Fraud Detection
Weak supervision model for healthcare fraud detection using knowledge-guided learning with limited labeled data.
2/24/2026
Lean Finder: Semantic Search for Mathlib That Understands User Intents
Semantic search engine for Lean theorem prover mathlib using intent-aware ranking for theorem discovery.
2/24/2026
On the Granularity of Causal Effect Identifiability
Causal inference research on state-based identifiability of causal effects in treatment-outcome relationships.
2/24/2026
Transitive RL: Value Learning via Divide and Conquer
RL algorithm using divide-and-conquer for offline goal-conditioned reinforcement learning value estimation.
2/24/2026
Bayesian Network Structure Discovery Using Large Language Models
Uses LLMs as core component for Bayesian network structure discovery from data, replacing traditional structure learning methods that require extensive observational data.
2/24/2026
Test-Time Adaptation for LLM Agents via Environment Interaction
Method for adapting LLM agents to novel environments through test-time interaction, addressing syntactic and semantic mismatches in observation formats and state dynamics.
2/24/2026
Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
Leak@k: study showing existing LLM unlearning methods fail under probabilistic decoding despite success under greedy decoding evaluation.
2/24/2026
Blind Inverse Game Theory: Jointly Decoding Rewards and Rationality in Entropy-Regularized Competitive Games
Blind-IGT: inverse game theory method jointly decoding rewards and rationality in entropy-regularized competitive games with unknown rationality parameter.
2/24/2026
Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning
Quasimetric learning method for goal-conditioned RL using multi-step returns to estimate temporal distance between observations over long horizons.
2/24/2026
FlowCast: Advancing Precipitation Nowcasting with Conditional Flow Matching
FlowCast: conditional flow matching method for radar-based precipitation nowcasting addressing uncertainty and high-dimensional data modeling.
2/24/2026
Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation
Gradient estimation method for multi-objective and meta reinforcement learning, partitioning n objectives into k groups for language model preference optimization.
2/24/2026
InTAct: Interval-based Task Activation Consolidation for Continual Learning
InTAct: continual learning approach using interval-based task activation consolidation with mathematical guarantees against catastrophic forgetting.
2/24/2026
MIST: Mutual Information Estimation Via Supervised Training
MIST: neural network-based mutual information estimator trained on 625K synthetic distributions with known ground-truth MI.
2/24/2026
E2E-GRec: An End-to-End Joint Training Framework for Graph Neural Networks and Recommender Systems
E2E-GRec framework for end-to-end joint training of GNNs and recommender systems, replacing two-stage pipeline approach.
2/24/2026
SelfAI: A self-directed framework for long-horizon scientific discovery
SelfAI multi-agent system for self-directed long-horizon scientific discovery with human-in-the-loop workflows and exploration trade-offs.
2/24/2026
ML-Tool-Bench: Tool-Augmented Planning for ML Tasks
ML-Tool-Bench framework for tool-augmented planning in autonomous ML agents orchestrating data analysis and model optimization workflows.
2/24/2026
Group Representational Position Encoding
GRAPE framework unifying positional encoding mechanisms using group actions for multiplicative rotations and additive biases.
2/24/2026
Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation
ECHO benchmark for evaluating graph neural networks on long-range graph propagation and interaction tasks.
2/24/2026
Clust-PSI-PFL: A Population Stability Index Approach for Clustered Non-IID Personalized Federated Learning
Clustered personalized federated learning framework using Population Stability Index to handle non-IID data across clients.
2/24/2026
Divided We Fall: Defending Against Adversarial Attacks via Soft-Gated Fractional Mixture-of-Experts with Randomized Adversarial Training
Soft-gated fractional mixture-of-experts with randomized adversarial training to defend ML models against adversarial attacks.
2/24/2026
Precision Autotuning for Linear Solvers via Reinforcement Learning
RL framework for adaptive precision tuning in linear solvers using contextual bandit approach to balance precision and efficiency.
2/24/2026
HeurekaBench: A Benchmarking Framework for AI Co-scientist
HeurekaBench benchmarking framework for evaluating LLM-based AI co-scientist agents on end-to-end scientific analysis tasks.
2/24/2026
Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias
Mathematical framework for polyphonic music generation using structural inductive bias and smart embeddings on Beethoven sonatas.
2/24/2026
Contrastive and Multi-Task Learning on Noisy Brain Signals with Nonlinear Dynamical Signatures
Multitask learning framework with denoising autoencoder for EEG signal analysis combining motor imagery and emotion recognition.
2/24/2026
Self-Augmented Mixture-of-Experts for QoS Prediction
Mixture-of-experts model with self-augmentation for Quality of Service prediction in web service recommendation systems.
2/24/2026
Inverting Self-Organizing Maps: A Unified Activation-Based Framework
Method for inverting Self-Organizing Maps as generative models using activation patterns and distance geometry to reconstruct inputs.
2/24/2026
PhysE-Inv: A Physics-Encoded Inverse Modeling approach for Arctic Snow Depth Prediction
Physics-informed inverse modeling framework for Arctic snow depth prediction combining process-based constraints with data-driven learning.
2/24/2026
FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
Machine unlearning method addressing long-tailed distributions in forget sets using forgetting-aware loss reweighting for privacy compliance.