4/7/2026
OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality
Optimization algorithm extending exponential moving average with adaptive rates and zero-noise optimality guarantees.
4/7/2026
A Grammar of Machine Learning Workflows
Formal grammar framework preventing data leakage in ML workflows through structural constraints and assessment gates.
4/7/2026
Hindsight-Anchored Policy Optimization: Turning Failure into Feedback in Sparse Reward Settings
Reinforcement learning method for post-training reasoning models using hindsight feedback in sparse reward environments.
4/7/2026
Security Considerations for Artificial Intelligence Agents
Security considerations and recommendations for AI agents from Perplexity based on operating agentic systems in production environments.
4/7/2026
Brittlebench: Quantifying LLM robustness via prompt sensitivity
Framework for measuring LLM robustness to prompt variations, typos, and alternative phrasings in real-world inputs.
4/7/2026
AI-Driven Predictive Maintenance with Environmental Context Integration for Connected Vehicles: Simulation, Benchmarking, and Field Validation
Predictive maintenance framework for connected vehicles integrating sensor and environmental data with ML models.
4/7/2026
Accelerating Byzantine-Robust Distributed Learning with Compressed Communication via Double Momentum and Variance Reduction
Distributed learning algorithm combining Byzantine robustness with communication compression for collaborative ML systems.
4/7/2026
Path-Constrained Mixture-of-Experts
Research on sparse Mixture-of-Experts architectures proposing expert path perspective to understand token routing patterns across layers.
4/7/2026
LLM-ODE: Data-driven Discovery of Dynamical Systems with Large Language Models
LLM-ODE: uses LLMs to discover governing equations of dynamical systems from data, improving on genetic programming approaches.
4/7/2026
ALMAB-DC: Active Learning, Multi-Armed Bandits, and Distributed Computing for Sequential Experimental Design and Black-Box Optimization
ALMAB-DC: sequential experimental design framework combining active learning, multi-armed bandits and distributed computing for black-box optimization.
4/7/2026
Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions
Federated learning approach combining Byzantine robustness and differential privacy for distributed training.
4/7/2026
Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning
Framework using LLMs to automatically design auxiliary reward programs for cooperative multi-agent reinforcement learning systems.
4/7/2026
Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch
Compares LLM agents against classical hyperparameter optimization algorithms using autoresearch testbed for tuning small language models.
4/7/2026
Optimal High-Probability Regret for Online Convex Optimization with Two-Point Bandit Feedback
Theoretical analysis of online convex optimization with two-point bandit feedback achieving tight regret bounds.
4/7/2026
ATLAS-RTC: Closing the Loop on LLM Agent Output with Token-Level Runtime Control
ATLAS-RTC: runtime control system for LLM agents enforcing structured output via token-level monitoring, biasing, masking and rollback.
4/7/2026
HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention
HISA: hierarchical indexing system for efficient sparse attention in LLMs, reducing indexer bottleneck in token-level sparse mechanisms.
4/7/2026
Rethinking Language Model Scaling under Transferable Hypersphere Optimization
Introduces HyperP, hypersphere parameterization for LLM scaling with improved stability and hyperparameter transfer.
4/7/2026
Beta-Scheduling: Momentum from Critical Damping as a Diagnostic and Correction Tool for Neural Network Training
Proposes time-varying momentum schedule derived from critically damped harmonic oscillator for neural network training optimization.
4/7/2026
On the Mirage of Long-Range Dependency, with an Application to Integer Multiplication
arXiv paper analyzing integer multiplication as hard problem for neural networks. Theoretical analysis challenging assumptions about long-range dependencies in neural computation.
4/7/2026
Realistic Market Impact Modeling for Reinforcement Learning Trading Environments
arXiv paper on realistic market impact modeling for RL trading agents. Gymnasium-compatible environments with nonlinear transaction costs for algorithmic trading research.
4/7/2026
Task-Centric Personalized Federated Fine-Tuning of Language Models
arXiv paper on personalized federated fine-tuning of language models. Federated learning approach for task-centric LLM adaptation on private distributed data.
4/7/2026
Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropout
arXiv paper on Byzantine-resilient distributed optimization with probabilistic edge dropout. Convergence analysis for distributed learning with adversarial agents.
4/7/2026
Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction
arXiv paper on memory-efficient LLM pre-training via truncated SVD factorization. Method reduces memory footprint for training large language models on consumer hardware.
4/7/2026
Using predefined vector systems to speed up neural network multimillion class classification
arXiv paper on O(1) complexity label prediction for neural networks with millions of classes. Optimization technique for efficient classification in high-dimensional spaces.
4/7/2026
Fatigue-Aware Learning to Defer via Constrained Optimisation
arXiv paper on human-AI cooperation via fatigue-aware deferral systems. ML method modeling human fatigue to optimize when AI should defer to humans.
4/7/2026
Screening Is Enough
arXiv paper introducing Multiscreen attention mechanism for language models. Alternative to softmax attention enabling absolute relevance scoring in transformers.
4/7/2026
Apriel-1.5-OpenReasoner: RL Post-Training for General-Purpose and Efficient Reasoning
arXiv paper on reinforcement learning post-training for reasoning models. Open-weight model training using verifiable rewards across diverse reasoning domains.
4/7/2026
Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning
arXiv paper on opponent modeling in game-theoretic reinforcement learning using tree-search and generative models. Research on scalable multi-agent RL methods.
4/7/2026
A Multi-Agent Reinforcement Learning Framework for Public Health Decision Analysis
Multi-agent reinforcement learning framework for HIV prevention policy optimization across U.S. regions.
4/7/2026
Robust Adaptation of Foundation Models with Black-Box Visual Prompting
Black-box visual prompting method for parameter-efficient transfer learning of foundation models without full parameter access.
4/7/2026
SPRIG: Improving Large Language Model Performance by System Prompt Optimization
SPRIG: Genetic algorithm for optimizing system prompts in LLMs to improve task performance.
4/7/2026
From XAI to MLOps: Explainable Concept Drift Detection with Profile Drift Detection
XAI-based method combining explainability with concept drift detection for monitoring model performance degradation.
4/7/2026
Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning
World models using disentangled representations to transfer semantic knowledge from distracting videos for RL agents.
4/7/2026
From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation
FSD framework combining vision-language models with robotic action models for zero-shot manipulation in novel scenarios.
4/7/2026
Gaussian mixture models as a proxy for interacting language models
Gaussian mixture models as computationally efficient proxy for LLM+RAG systems combining multiple models.
4/7/2026
All is Not Lost: LLM Recovery without Checkpoints
Technique to recover LLM training on decentralized/spot nodes from partial model loss without full checkpoints.
4/7/2026
Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models
Method for LLMs to reliably cite source documents seen during training without external retrievers at inference time.
4/7/2026
WhisperRT -- Turning Whisper into a Causal Streaming Model
Modification of Whisper ASR model to enable low-latency streaming transcription through architectural and training changes.
4/7/2026
Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
Vision-language model for robotic manipulation using embodiment-agnostic pointing representation to address generalization in embodied AI.
4/7/2026
ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference
System co-design for efficient on-device LLM inference on NPU hardware, optimizing attention operations for privacy-preserving deployment.
4/7/2026
Smart Paste: Automatically Fixing Copy/Paste for Google Developers
Google developer tool using deep learning to automatically fix copy/paste code, predicting required edits from formatting to cross-language translation.
4/7/2026
EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
Knowledge editing method for LLMs enabling sequential updates through null-space alignment, improving robustness in continual model editing scenarios.
4/7/2026
Three-dimensional inversion of gravity data using implicit neural representations and scientific machine learning
Scientific machine learning approach using implicit neural representations for 3D gravity inversion, modeling subsurface density as continuous field.
4/7/2026
Image Hashing via Cross-View Code Alignment in the Age of Foundation Models
Image hashing method using foundation models for efficient large-scale retrieval with compact binary codes instead of high-dimensional embeddings.
4/7/2026
Contradictions in Context: Challenges for Retrieval-Augmented Generation in Healthcare
Study of RAG limitations in healthcare domain, showing how retrieval-augmented generation fails when source documents contain contradictory or outdated information.
4/7/2026
SPHINX: A Synthetic Environment for Visual Perception and Reasoning
Sphinx synthetic environment for visual perception and reasoning with procedurally generated puzzles covering 25 task types, enabling precise evaluation and large-scale dataset construction.
4/7/2026
Optical Context Compression Is Just (Bad) Autoencoding
Analysis showing optical context compression via vision tokens is functionally equivalent to lossy autoencoding, questioning effectiveness of DeepSeek-OCR's compression pipeline.
4/7/2026
Agile Deliberation: Concept Deliberation for Subjective Visual Classification
Human-in-the-loop approach for visual classification through iterative concept deliberation, addressing subjective vision tasks in content moderation and curation.
4/7/2026
The Drill-Down and Fabricate Test (DDFT): A Protocol for Measuring Epistemic Robustness in Language Models
DDFT protocol measures epistemic robustness of language models under stress conditions, distinguishing knowledge gaps from verification mechanism failures beyond static benchmarks.
4/7/2026
Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers
Mechanistic interpretability study of how Diffusion Transformers generate correct spatial relations in text-to-image generation.