3/20/2026
Enhancing the Parameterization of Reservoir Properties for Data Assimilation Using Deep VAE-GAN
Deep VAE-GAN approach improving reservoir parameterization for data assimilation in petroleum reservoir simulation.
3/20/2026
Automatic Configuration of LLM Post-Training Pipelines
AutoPipe framework for automatically configuring LLM post-training pipelines combining supervised fine-tuning and reinforcement learning under budget constraints.
3/20/2026
Seasoning Generative Models for a Generalization Aftertaste
Study on using discriminators to enhance generative model training across GANs, weak learner frameworks, and diffusion models.
3/20/2026
DriftGuard: Mitigating Asynchronous Data Drift in Federated Learning
Method mitigating asynchronous data drift in federated learning where different devices experience different distribution shifts.
3/20/2026
Uniform a priori bounds and error analysis for the Adam stochastic gradient descent optimization method
Theoretical error analysis of Adam optimizer for training deep neural networks and beyond, addressing open research gaps.
3/20/2026
Neural Galerkin Normalizing Flow for Transition Probability Density Functions of Diffusion Models
Framework using normalizing flows to approximate diffusion process transition probability densities by solving Fokker-Planck equations.
3/20/2026
Context Bootstrapped Reinforcement Learning
Method augmenting reinforcement learning from verifiable rewards with context bootstrapping to improve exploration and reasoning pattern acquisition.
3/20/2026
BVSIMC: Bayesian Variable Selection-Guided Inductive Matrix Completion for Improved and Interpretable Drug Discovery
Bayesian model for drug discovery incorporating variable selection and side information through inductive matrix completion.
3/20/2026
Maximum-Entropy Exploration with Future State-Action Visitation Measures
Intrinsic reward method for reinforcement learning agents maximizing entropy of future state-action visitation distributions.
3/20/2026
Book your room in the Turing Hotel! A symmetric and distributed Turing Test with multiple AIs and humans
Novel symmetric Turing Test variant where groups of LLMs and humans interact, judge, and respond in time-bounded discussions.
3/20/2026
AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science
Benchmarking study comparing AI agents' performance to human experts on domain-specific data science tasks, evaluating LLM-based automation of data science workflows.
3/20/2026
When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence
Analysis of differential privacy guarantees and convergence in wireless federated learning without restrictive convexity assumptions.
3/20/2026
Communication-Efficient and Robust Multi-Modal Federated Learning via Latent-Space Consensus
CoMFed framework for communication-efficient federated learning with heterogeneous multimodal clients and privacy preservation.
3/20/2026
Position: Spectral GNNs Are Neither Spectral Nor Superior for Node Classification
Theoretical analysis questioning foundations of Spectral Graph Neural Networks for node classification tasks.
3/20/2026
On Optimizing Multimodal Jailbreaks for Spoken Language Models
Study of multimodal jailbreak attacks on Spoken Language Models using gradient-based optimization across text and audio modalities.
3/20/2026
From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models
Research on efficiency metrics for Vision-Language-Action embodied agents, showing that parameter/FLOP counts don't reflect real robotic platform performance.
3/20/2026
Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection
Continual learning method using random projection layers with pretrained models for improved representation learning.
3/20/2026
DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge
DyMoE: dynamic expert selection with mixed-precision quantization for efficient MoE model inference on edge devices.
3/20/2026
SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits
SOL-ExecBench: 235-problem benchmark for CUDA kernel optimization against hardware efficiency limits for agentic AI systems.
3/20/2026
MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
MIDST challenge evaluating membership inference attacks on synthetic tabular data generated by diffusion models.
3/20/2026
Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction
CONSTRUCT method for real-time trustworthiness scoring of LLM structured outputs and field-level error detection.
3/20/2026
MineDraft: A Framework for Batch Parallel Speculative Decoding
MineDraft framework for batch parallel speculative decoding to accelerate LLM inference by hiding draft and verify stages.
3/20/2026
Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems
Corpus poisoning attacks and defenses for RAG systems, demonstrating vulnerabilities in LLM-extended retrieval pipelines.
3/20/2026
Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling
Quantization-aware drift correction method for diffusion model sampling to reduce degradation from post-training quantization noise.
3/20/2026
Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
Few-shot learning adapter for CLIP using patch-level and text supervision without increasing inference costs.
3/20/2026
STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling
Defense mechanism against backdoor attacks in audio/speech models using stability-based trigger detection at inference time.
3/20/2026
Transfer Learning for Contextual Joint Assortment-Pricing under Cross-Market Heterogeneity
Transfer learning for pricing and assortment optimization across markets using multinomial logit choice models with bandit feedback.
3/20/2026
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models
Insight-V++ framework enables multi-agent visual reasoning for MLLMs with long-chain reasoning, addressing data scarcity and training optimization.
3/20/2026
Auditing Preferences for Brands and Cultures in LLMs
ChoiceEval framework audits brand and cultural preference biases in LLMs to assess market fairness and information diversity risks.
3/20/2026
MemArchitect: A Policy Driven Memory Governance Layer
MemArchitect adds governance layer for LLM agent memory management, handling contradictions, privacy, and outdated information in persistent RAG systems.
3/20/2026
Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought
VCoT-Bench evaluates LLMs on Rust program verification via chain-of-thought reasoning, testing logical deduction abilities beyond binary pass/fail.
3/20/2026
Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model
Method for reliable uncertainty quantification in Vision-Language-Action models by shifting focus to safety-critical moments in robotic control.
3/20/2026
PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching
PowerFlow applies principled distribution matching to unsupervised reinforcement learning from LLM internal feedback without external supervision.
3/20/2026
TARo: Token-level Adaptive Routing for LLM Test-time Alignment
TARo enables frozen LLMs to perform structured reasoning at inference time through token-level adaptive routing, avoiding expensive post-training alignment.
3/20/2026
From Topic to Transition Structure: Unsupervised Concept Discovery at Corpus Scale via Predictive Associative Memory
Unsupervised discovery of transition-structure concepts in text via temporal co-occurrence patterns using contrastive learning on large corpus.
3/20/2026
UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference
Adaptive context allocation method for LLM long-context inference using uncertainty-triggered token-level budgeting to address attention dilution.
3/20/2026
T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World
Vision-language model method for temporal out-of-distribution detection and domain generalization in open-world settings using adaptive pattern matching.
3/20/2026
The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
Analysis of how standard LLM decoding strategies (top-k, nucleus sampling) exclude contextually appropriate but statistically rare tokens compared to human language production.
3/20/2026
When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making
ICE-Guard detects spurious feature reliance in LLM decision-making through intervention consistency testing on demographic, authority, and framing features.
3/20/2026
Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds
Addresses sim-to-real transfer for vision-language-action models in robotics by generating diverse 3D simulation worlds for RL fine-tuning.
3/20/2026
iSatCR: Graph-Empowered Joint Onboard Computing and Routing for LEO Data Delivery
iSatCR optimizes onboard computing and routing for LEO satellite data processing using graph neural networks to reduce ground transmission bottlenecks.
3/20/2026
CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention
CausalVAD applies causal intervention to de-confound end-to-end autonomous driving models, addressing dataset bias and improving reliability.
3/20/2026
ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs
ICE framework evaluates explanation faithfulness in LLMs via randomization tests with multiple intervention operators, distinguishing genuine faithfulness from chance.
3/20/2026
Memento-Skills: Let Agents Design Agents
Memento-Skills introduces an LLM agent that autonomously designs and improves task-specific agents through continual learning with stateful prompts and reusable skills.
3/20/2026
Learn for Variation: Variationally Guided AAV Trajectory Learning in Differentiable Environments
Proposes variational guidance for autonomous aerial vehicle trajectory learning to address credit assignment and training instability in sparse reward RL settings.
3/20/2026
BeamAgent: LLM-Aided MIMO Beamforming with Decoupled Intent Parsing and Alternating Optimization for Joint Site Selection and Precoding
BeamAgent combines LLMs with wireless beamforming optimization through decoupled intent parsing and alternating optimization, separating LLM reasoning from numerical computation.
3/20/2026
RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models
RewardFlow proposes topology-aware reward propagation on state graphs for RL-enhanced LLM agents, addressing sparse reward limitations without expensive dedicated reward models.
3/20/2026
From Accuracy to Readiness: Metrics and Benchmarks for Human-AI Decision-Making
Proposes evaluation framework beyond accuracy for human-AI collaborative decision-making, addressing miscalibrated reliance and team effectiveness.
3/20/2026
Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought
Studies entropy trajectory shape in chain-of-thought reasoning to predict LLM correctness without additional inference, testing on GSM8K with Qwen2.5-7B.
3/20/2026
Unified Taxonomy for Multivariate Time Series Anomaly Detection using Deep Learning
Proposes unified taxonomy with 11 dimensions for categorizing deep learning approaches to multivariate time series anomaly detection.