3/18/2026
Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
Attribution-guided sparse feature steering to mitigate hallucinations in large vision-language models without increasing inference cost.
3/18/2026
Learning to Predict, Discover, and Reason in High-Dimensional Discrete Event Sequences
Deep learning method for discovering error patterns in automotive diagnostic trouble codes and vehicle system fault characterization.
3/18/2026
Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI
YOLO-based deep learning framework for automated wasp identification with explainable AI integration for biodiversity assessment.
3/18/2026
PashtoCorp: A 1.25-Billion-Word Corpus, Evaluation Suite, and Reproducible Pipeline for Low-Resource Language Development
1.25B-word corpus for Pashto with reproducible NLP pipeline, deduplication, and quality filtering across 39 sources.
3/18/2026
Controlling Fish Schools via Reinforcement Learning of Virtual Fish Movement
Reinforcement learning approach training virtual fish to control real fish schools, using 2D screen-displayed agents as alternatives to physical robots.
3/18/2026
REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models
Multi-modal adversarial attacks exposing vulnerabilities in image generation model unlearning without full retraining.
3/18/2026
Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models
Omanic benchmark for step-level evaluation of multi-hop reasoning in LLMs with annotations for diagnosing reasoning failures.
3/18/2026
When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making
Framework for resource-aware LLM reasoning in embodied robotic agents using reinforcement learning to balance computation and action execution.
3/18/2026
Probing Cultural Signals in Large Language Models through Author Profiling
Evaluation of cultural biases in LLMs through author profiling from song lyrics, detecting gender and ethnicity inference in zero-shot settings.
3/18/2026
Finding Common Ground in a Sea of Alternatives
Formal model for selecting statements that find common ground across diverse population preferences using generative AI.
3/18/2026
Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights
Analysis of conformal factuality robustness in retrieval-augmented generation LLM systems, proposing novel metrics for hallucination evaluation.
3/18/2026
ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K
Pipeline generating 100K data-generation-ready 3D digital object twins from single images for robotic manipulation simulation.
3/18/2026
Leveraging Imperfect Sources to Detect Fairwashing in Black-Box Auditing
Method for detecting fairwashing in black-box algorithmic auditing by identifying compliant surrogate models versus discriminatory production systems.
3/18/2026
Revisiting ASR Error Correction with Specialized Models
Research on correcting automatic speech recognition errors using compact seq2seq models trained on real and synthetic ASR error patterns, avoiding LLM latency and hallucination issues.
3/18/2026
SG-DeepONet: Source-generalized deep operator learning for full waveform inversion
Deep operator learning for full waveform inversion addressing source generalization by training on diverse seismic source conditions.
3/18/2026
Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
TS-Reasoner: domain-specialized LLM agent for multi-step time series reasoning and analysis, integrating language model reasoning with domain-specific computation.
3/18/2026
Anomaly Resilient Temporal QoS Prediction using Hypergraph Convoluted Transformer Network
Hypergraph convolutional transformer for QoS prediction handling data sparsity and cold-start issues in service recommendations.
3/18/2026
Learning-based Sketches for Frequency Estimation in Data Streams without Ground Truth
Learning-augmented sketches for frequency estimation in data streams without ground truth labels, improving over traditional memory-constrained methods.
3/18/2026
When Machine Learning Gets Personal: Evaluating Prediction and Explanation
Framework quantifying impacts of model personalization on prediction accuracy and explanation quality in high-stakes domains like healthcare.
3/18/2026
Reevaluating Policy Gradient Methods for Imperfect-Information Games
Reevaluation of policy gradient methods (PPO) for imperfect-information games, questioning necessity of complex DRL algorithms based on fictitious play and CFR.
3/18/2026
Optimal Denoising in Score-Based Generative Models: The Role of Data Regularity
Analysis of optimal denoising in score-based generative models, comparing full-denoising vs half-denoising under data regularity assumptions.
3/18/2026
MASS: MoErging through Adaptive Subspace Selection
MASS: adaptive subspace selection method for model merging, combining multiple fine-tuned models without training overhead while matching separate endpoint accuracy.
3/18/2026
Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
RL finetuning for text-to-multiview diffusion models to improve few-step generation quality, balancing per-view fidelity and cross-view consistency.
3/18/2026
Memorization to Generalization: Emergence of Diffusion Models from Associative Memory
Dense associative memories framework showing emergence of diffusion models from memory storage, bridging memorization and generalization in neural networks.
3/18/2026
VERINA: Benchmarking Verifiable Code Generation
VERINA benchmark for evaluating LLM code generation with jointly generated specifications and proofs, addressing correctness verification challenges.
3/18/2026
Coded Robust Aggregation for Distributed Learning under Byzantine Attacks
Coded robust aggregation method for distributed learning resilient to Byzantine attacks, improving gradient aggregation in federated settings.
3/18/2026
Out-of-Distribution Graph Models Merging
Graph model merging technique for combining GNN models pre-trained on different domains with distribution discrepancy to create generalized models.
3/18/2026
Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning
Knowledge graph embedding methods for feature learning on large-scale graphs as external knowledge for downstream ML tasks, optimizing beyond link prediction.
3/18/2026
On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
Dynamic weighting approach combining supervised fine-tuning and reinforcement learning for LLM post-training, unifying on-policy and off-policy learning paradigms.
3/18/2026
Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
Tool-augmented LLM agents trained with synthetic code environments via RL to improve generalization on tool-use tasks, addressing brittleness with new tools and unseen workflows.
3/18/2026
LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning
LANCE: low-rank activation compression method for efficient on-device continual learning, reducing memory costs during backpropagation in resource-constrained environments.
3/18/2026
NanoFlux: Adversarial Dual-LLM Evaluation and Distillation For Multi-Domain Reasoning
NanoFlux: adversarial dual-LLM framework for generating targeted training data to improve reasoning, achieving strong results with <200 examples through competitive Attacker-Defender dynamics.
3/18/2026
Attribution-Guided Decoding
Attribution-Guided Decoding uses interpretability to improve LLM instruction-following and factual accuracy.
3/18/2026
PolyGraph Discrepancy: a classifier-based metric for graph generation
PolyGraph Discrepancy metric provides absolute performance measure for graph generative models.
3/18/2026
Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
Tree search guidance method for controllable graph generation with diffusion models.
3/18/2026
Connecting Jensen-Shannon and Kullback-Leibler Divergences: A New Bound for Representation Learning
Theoretical bounds connecting Jensen-Shannon and Kullback-Leibler divergences for representation learning.
3/18/2026
Transformers can do Bayesian Clustering
Cluster-PFN extends Prior-Data Fitted Networks to Bayesian clustering with uncertainty quantification.
3/18/2026
AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs
AGRAG improves graph-based RAG for LLMs by addressing hallucination, reasoning, and answer quality issues.
3/18/2026
FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD
FedSDWC applies causal learning to federated learning for handling out-of-distribution data shifts.
3/18/2026
Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning
MAVA accelerates masked auto-regressive diffusion inference for practical reinforcement learning applications.
3/18/2026
Tail Distribution of Regret in Optimistic Reinforcement Learning
Derives tail distribution bounds for regret in optimism-based reinforcement learning algorithms.
3/18/2026
Flow Matching for Tabular Data Synthesis
Empirical comparison of flow matching variants with diffusion models for privacy-preserving tabular data synthesis.
3/18/2026
Language as a Wave Phenomenon: Semantic Phase Locking and Interference in Neural Networks
PRISM complex-valued encoder explores phase relationships in semantic representations of neural sequence models.
3/18/2026
Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
Method to identify and measure social biases in text-to-image diffusion models via automated prompt search.
3/18/2026
SolarGPT-QA: A Domain-Adaptive Large Language Model for Educational Question Answering in Space Weather and Heliophysics
Domain-adapted LLM fine-tuned for educational QA in space weather and heliophysics.
3/18/2026
Scalable Sample-Level Causal Discovery in Event Sequences via Autoregressive Density Estimation
TRACE framework uses autoregressive density estimation for causal discovery in single event sequences.
3/18/2026
A Scalable Approach to Solving Simulation-Based Network Security Games
MetaDOAR meta-controller applies multi-agent reinforcement learning to large-scale cyber-network security games.
3/18/2026
Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns
TRC² architecture enables LLMs to continually learn and adapt without catastrophic forgetting through specialized decoder design.
3/18/2026
Transit Network Design with Two-Level Demand Uncertainties: A Machine Learning and Contextual Stochastic Optimization Framework
Framework combining ML and contextual stochastic optimization for transit network design under demand uncertainty.
3/18/2026
AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
AOI framework enabling LLM agents to improve from failed cloud diagnosis trajectories in SRE automation with safety constraints.