2/20/2026
What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else?
Analysis of security vulnerabilities in embodied AI systems including LLM-driven agents, autonomous vehicles, and service robots.
2/20/2026
A feature-stable and explainable machine learning framework for trustworthy decision-making under incomplete clinical data
Machine learning framework for trustworthy clinical decision-making with feature stability under incomplete data.
2/20/2026
Voice-Driven Semantic Perception for UAV-Assisted Emergency Networks
Framework for integrating voice communications with UAV-assisted emergency networks using semantic perception.
2/20/2026
SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery
SpectralGCD method for generalized category discovery using spectral concept selection and cross-modal representation learning.
2/20/2026
Improving LLM-based Recommendation with Self-Hard Negatives from Intermediate Layers
Research on improving LLM-based recommendation systems using self-hard negatives from intermediate layers for better preference learning during fine-tuning.
2/20/2026
Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study
Taxonomy and comparative study of uncertainty quantification methods for detecting hallucinations in long-form LLM outputs.
2/20/2026
Beyond Pipelines: A Fundamental Study on the Rise of Generative-Retrieval Architectures in Web Research
Study on generative-retrieval architectures in web search and how LLMs have transformed information retrieval practices.
2/20/2026
Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge
arXiv paper on Jolt Atlas, a zero-knowledge ML framework for verifiable ONNX tensor operation inference using lookup arguments.
2/20/2026
What Do LLMs Associate with Your Name? A Human-Centered Black-Box Audit of Personal Data
Audit of personal data associations in 8 LLMs using LMP2 privacy probe, examining how models retain and surface personal information.
2/20/2026
Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection
arXiv paper on image copy detection using self-supervised learning with patch-level contrastive learning for manipulated content.
2/20/2026
Learning with Boolean threshold functions
arXiv paper on training neural networks with Boolean threshold functions where all node values are strictly ±1.
2/20/2026
LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights
arXiv paper introducing LORA-CRAFT, a parameter-efficient fine-tuning method using Tucker decomposition on transformer attention weights.
2/20/2026
The Anxiety of Influence: Bloom Filters in Transformer Attention Heads
arXiv paper identifying transformer attention heads functioning as membership filters, analyzing their spectrum of testing strategies across language models.
2/20/2026
Position: Evaluation of ECG Representations Must Be Fixed
Position paper arguing current ECG representation learning benchmarks must be revised to align with clinically meaningful objectives.
2/20/2026
Systematic Evaluation of Single-Cell Foundation Model Interpretability Reveals Attention Captures Co-Expression Rather Than Unique Regulatory Signal
arXiv paper systematically evaluating mechanistic interpretability in single-cell foundation models using 37 analyses and 153 tests.
2/20/2026
Toward a Fully Autonomous, AI-Native Particle Accelerator
Position paper proposing AI co-design for autonomous particle accelerator operation with minimal human intervention.
2/20/2026
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
arXiv paper introducing MASPO, a reinforcement learning method improving gradient utilization and probability mass handling for LLM reasoning.
2/20/2026
Probability-Invariant Random Walk Learning on Gyral Folding-Based Cortical Similarity Networks for Alzheimer's and Lewy Body Dementia Diagnosis
arXiv paper on gyral folding-based cortical networks for Alzheimer's and Lewy body dementia diagnosis.
2/20/2026
Be Wary of Your Time Series Preprocessing
arXiv paper analyzing how normalization strategies impact Transformer expressivity for time series representation learning.
2/20/2026
Conditional Flow Matching for Continuous Anomaly Detection in Autonomous Driving on a Manifold-Aware Spectral Space
arXiv paper on Deep-Flow, an unsupervised anomaly detection framework for autonomous vehicles using optimal transport conditional flow matching.
2/20/2026
The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\rightarrow$LLM Pipelines?
arXiv paper testing whether speech LLMs behave identically to ASR-to-LLM cascades across four models and six tasks.
2/20/2026
Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery
arXiv paper on relevance-guided online meta-learning for geospatial discovery under resource constraints and dynamic environments.
2/20/2026
Towards Anytime-Valid Statistical Watermarking
arXiv paper on anytime-valid statistical watermarking for distinguishing machine-generated content from human text in LLMs.
2/20/2026
Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
arXiv paper on variance control in asynchronous off-policy RL for LLMs, addressing high variance from stale rollouts in critic-free methods.
2/20/2026
When to Trust the Cheap Check: Weak and Strong Verification for Reasoning
arXiv paper analyzing weak vs strong verification mechanisms in LLM reasoning systems, examining cost-reliability tradeoffs in verification loops.
2/20/2026
Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting
arXiv paper on Reverso, a time series foundation model for zero-shot forecasting that scales to hundreds of millions of parameters.
2/20/2026
FAMOSE: A ReAct Approach to Automated Feature Discovery
FAMOSE: ReAct-based agent for automated feature engineering in tabular data that autonomously explores and generates optimal features without domain expertise.
2/20/2026
Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting
Black-box adversarial attack method on Large Vision-Language Models using fine-grained detail targeting to address gradient-free optimization challenges.
2/20/2026
MARS: Margin-Aware Reward-Modeling with Self-Refinement
MARS framework for reward modeling using margin-aware training and self-refinement to reduce reliance on costly human-labeled preference data.
2/20/2026
Sink-Aware Pruning for Diffusion Language Models
Novel pruning technique for Diffusion Language Models that optimizes inference efficiency by reconsidering attention sink preservation assumptions.
2/20/2026
Goal Inference from Open-Ended Dialog
Research on embodied AI agents using LLMs for open-ended dialog to infer and accomplish diverse user goals efficiently and robustly.
2/20/2026
GAI: Generative Agents for Innovation
GAI: multi-agent LLM framework with reflection and dialogue for collective reasoning to drive innovation.
2/20/2026
AI-Assisted Decision Making with Human Learning
Framework studying AI-assisted human decision-making where humans learn through repeated interactions with algorithms.
2/20/2026
Capturing Individual Human Preferences with Reward Features
Method for learning user-specific reward models in RLHF to capture individual preferences in LLM training.
2/20/2026
A Scalable Framework for Evaluating Health Language Models
Evaluation framework for assessing health-focused LLMs on personalized response quality with scalable methodology.
2/20/2026
The Correspondence Between Bounded Graph Neural Networks and Fragments of First-Order Logic
Theoretical correspondence between bounded GNNs and first-order logic fragments characterizing expressive power.
2/20/2026
Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning
∞-THOR: framework for long-horizon embodied AI tasks with benchmark testing long-context reasoning across extended trajectories.
2/20/2026
$\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts
SPECS: method for faster test-time scaling in LLMs using speculative drafts to reduce latency while maintaining performance.
2/20/2026
Sufficient, Necessary and Complete Causal Explanations in Image Classification
Formal causal explanations for image classifier decisions using logic-based approaches.
2/20/2026
Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems
Bongard-RWR+: benchmark for abstract visual reasoning with fine-grained concepts using real-world images.
2/20/2026
Drones that Think on their Feet: Sudden Landing Decisions with Embodied AI
Embodied AI system enabling autonomous drones to make adaptive decisions for sudden events using visual language models.
2/20/2026
Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
PROBE: benchmark for measuring proactive problem-solving in LLM agents across extended contexts and time horizons.
2/20/2026
Bridging Symbolic Control and Neural Reasoning in LLM Agents: Structured Cognitive Loop with a Governance Layer
SCL: modular agent architecture separating cognition into five phases with soft symbolic control governance layer for LLM agents.
2/20/2026
CaveAgent: Transforming LLMs into Stateful Runtime Operators
CaveAgent: framework converting LLM-as-text-generator to LLM-as-runtime-operator with dual-stream architecture for long-horizon task execution.
2/20/2026
Puzzle it Out: Local-to-Global World Model for Offline Multi-Agent Reinforcement Learning
Offline multi-agent RL using local-to-global world models to enable conservative policies to generalize beyond dataset support.
2/20/2026
Autonomous Business System via Neuro-symbolic AI
AUTOBUS: neuro-symbolic AI system combining LLMs with deterministic logic for autonomous business process reconfiguration and execution.
2/20/2026
Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection
SpikeScore: method for cross-domain hallucination detection in LLMs that generalizes across different domains better than existing approaches.
2/20/2026
Autonomous Data Processing using Meta-Agents
ADP-MA: framework for autonomous data processing using meta-agents that monitor, manage, and optimize end-to-end pipelines after deployment.
2/20/2026
An Adaptive Differentially Private Federated Learning Framework with Bi-level Optimization
Federated learning framework addressing device heterogeneity and non-IID data with differential privacy using bi-level optimization.
2/20/2026
EduEVAL-DB: A Role-Based Dataset for Pedagogical Risk Evaluation in Educational Explanations
EduEVAL-DB dataset for training AI tutors to evaluate pedagogical quality of educational explanations across K-12 subjects.