2/20/2026
The Chicken and Egg Dilemma: Co-optimizing Data and Model Configurations for LLMs
Method for jointly optimizing data mixture and model architecture configurations during LLM training to avoid suboptimal individual choices.
2/20/2026
Diffusion-Guided Pretraining for Brain Graph Foundation Models
Diffusion-guided pretraining approach for brain graph foundation models using semantic-aware augmentation strategies.
2/20/2026
Biases in the Blind Spot: Detecting What LLMs Fail to Mention
Automated black-box pipeline for detecting unverbalized biases in LLM reasoning traces and chain-of-thought explanations.
2/20/2026
Universal Diffusion-Based Probabilistic Downscaling
Universal diffusion-based framework for converting low-resolution weather forecasts to probabilistic high-resolution predictions without model fine-tuning.
2/20/2026
Logit Distance Bounds Representational Similarity
Analysis showing logit distance bounds representational similarity in discriminative models including autoregressive language models.
2/20/2026
Omni-iEEG: A Large-Scale, Comprehensive iEEG Dataset and Benchmark for Epilepsy Research
Large-scale intracranial EEG dataset and benchmarks for epilepsy research and seizure localization using data-driven approaches.
2/20/2026
HPMixer: Hierarchical Patching for Multivariate Time Series Forecasting
HPMixer model for long-term multivariate time series forecasting using hierarchical patching to capture periodic patterns and residuals.
2/20/2026
A Parameter-free Adaptive Resonance Theory-based Topological Clustering Algorithm Capable of Continual Learning
ART-based topological clustering algorithm that eliminates need for manual parameter tuning and supports continual learning.
2/20/2026
A Parametric Contextual Online Learning Theory of Brokerage
Online learning theory framework for contextual brokerage between traders with sequential asset trading decisions.
2/20/2026
Input-Label Correlation Governs a Linear-to-Nonlinear Transition in Random Features under Spiked Covariance
Theoretical analysis of linear-to-nonlinear transition in random feature models under spiked covariance and input-label correlation.
2/20/2026
Goal Inference from Open-Ended Dialog
Framework for embodied AI agents to infer user goals from open-ended dialog using LLMs for efficient task accomplishment.
2/20/2026
Multi-View 3D Reconstruction using Knowledge Distillation
Knowledge distillation pipeline to compress Dust3r foundation model for efficient 3D reconstruction and visual localization.
2/20/2026
Efficient Context Propagating Perceiver Architectures for Auto-Regressive Language Modeling
Perceiver architecture for auto-regressive language modeling reducing attention complexity from quadratic to semi-linear.
2/20/2026
Enhancing Multilingual LLM Pretraining with Model-Based Data Selection
Model-based data filtering framework for multilingual LLM pretraining that identifies diverse, high-quality training samples.
2/20/2026
Simple Self Organizing Map with Vision Transformers
Combining Self-Organizing Maps with Vision Transformers to improve performance on smaller datasets through explicit inductive biases.
2/20/2026
Capturing Individual Human Preferences with Reward Features
Learning user-specialized reward models for reinforcement learning from human feedback to capture individual preference disagreement.
2/20/2026
Cert-SSBD: Certified Backdoor Defense with Sample-Specific Smoothing Noises
Certified defense against backdoor attacks in deep neural networks using sample-specific smoothing noise.
2/20/2026
A Unifying Framework for Robust and Efficient Inference with Unstructured Data
Framework for handling unstructured data feature extraction with neural networks while accounting for measurement bias in economic analysis.
2/20/2026
ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
ReplaceMe: training-free depth pruning method replacing transformer blocks with linear operations for efficient model compression.
2/20/2026
Inferring entropy production in many-body systems using nonequilibrium maximum entropy
Method for inferring entropy production in high-dimensional stochastic systems using nonequilibrium maximum entropy principle.
2/20/2026
LLM Fingerprinting via Semantically Conditioned Watermarks
LLM fingerprinting via semantically conditioned watermarks that survive finetuning and quantization without being easily detected.
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 Needle(s) in Embodied Haystack benchmark for testing long-context reasoning in agents.
2/20/2026
Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models
Using persona-driven prompting to simulate European Parliament voting behavior with LLMs, addressing political bias in model responses.
2/20/2026
Nonlinear Model Order Reduction of Dynamical Systems in Process Engineering: Review and Comparison
Review of nonlinear model order reduction methods for creating computationally efficient dynamical system models in process engineering.
2/20/2026
$\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts
SPECS: method for faster test-time scaling in LLMs through speculative drafts, balancing reasoning accuracy with user-facing latency.
2/20/2026
Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems
Bongard Problems benchmark using real-world images to test abstract visual reasoning and fine-grained concept identification in models.
2/20/2026
Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction
Proposes inference-time search algorithm that guides diffusion model sampling with side information for improved image reconstruction in inverse problems.
2/20/2026
LayerSync: Self-aligning Intermediate Layers
LayerSync regularizes diffusion models using their own intermediate layer representations to improve generation quality and training efficiency.
2/20/2026
Toward LLM-Supported Automated Assessment of Critical Thinking Subskills
Uses LLMs for automated assessment of critical thinking skills in educational contexts, addressing evaluation of evidence and claim reliability.
2/20/2026
A Study on Inference Latency for Vision Transformers on Mobile Devices
Benchmarks inference latency of 190 Vision Transformers on mobile devices compared to CNNs, analyzing architectural factors affecting performance.
2/20/2026
Multimodal Wireless Foundation Models
Extends wireless foundation models to accept multiple input modalities for improved task performance and adaptation across varying conditions.
2/20/2026
AI/ML based Joint Source and Channel Coding for HARQ-ACK Payload
Applies transformer-based deep learning for joint source-channel coding of non-uniformly distributed HARQ-ACK bits in wireless communications.
2/20/2026
Block-Recurrent Dynamics in Vision Transformers
Introduces Block-Recurrent Hypothesis explaining Vision Transformer depth as block-recurrent computational flow for mechanistic interpretation.
2/20/2026
Puzzle it Out: Local-to-Global World Model for Offline Multi-Agent Reinforcement Learning
Proposes world model approach for offline multi-agent RL using local-to-global puzzle solving to overcome conservative policies and improve generalization.
2/20/2026
Beyond Predictive Uncertainty: Reliable Representation Learning with Structural Constraints
Framework for treating representation reliability as a first-class property in machine learning, beyond traditional predictive uncertainty quantification.
2/20/2026
Laser interferometry as a robust neuromorphic platform for machine learning
Proposes implementing optical neural networks using linear optical resources and phase-shift encoding for neuromorphic machine learning hardware.
2/20/2026
Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection
SpikeScore method for detecting LLM hallucinations that generalizes across domains, addressing the gap in cross-domain hallucination detection for real-world deployment.
2/20/2026
Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors
Theoretical analysis showing fixed-budget and fixed-confidence best-arm identification in K-armed bandits have equivalent optimal sample complexities up to logarithmic factors.
2/20/2026
Universal Coefficients and Mayer-Vietoris Sequence for Groupoid Homology
Mathematical study of homology in ample groupoids using Moore complexes and continuous étale homomorphisms, with Mayer-Vietoris sequences.
2/20/2026
Accelerating Large-Scale Dataset Distillation via Exploration-Exploitation Optimization
Proposes exploration-exploitation optimization for dataset distillation to compress large datasets into synthetic versions while maintaining model performance.
2/20/2026
Building Safe and Deployable Clinical Natural Language Processing under Temporal Leakage Constraints
Addresses temporal leakage in clinical NLP models for discharge planning, proposing methods to prevent overconfident predictions from deployment artifacts.
2/20/2026
Conjugate Learning Theory: Uncovering the Mechanisms of Trainability and Generalization in Deep Neural Networks
Conjugate learning theory framework characterizes trainability and generalization of deep neural networks using convex duality and mini-batch SGD analysis.
2/20/2026
EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments
CoreCraft is a high-fidelity enterprise RL simulation environment with 2,500+ entities and 23 tools for training generalizable AI agents in customer support scenarios.
2/20/2026
Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
STING benchmark measures how LLM agents can be misused over multiple turns and across languages to assist with illegal tasks, testing multi-step harmful goal execution.
2/20/2026
RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation
RoboGene uses an agentic framework to automatically generate diverse robotic manipulation tasks for training vision-language-action models, addressing data scarcity in robot learning.
2/20/2026
AI Impact Summit 2026: How we're partnering to make AI work for everyone
Google announces AI Impact Summit 2026 partnerships and investments for broad AI adoption, marketing content with limited technical depth.
2/20/2026
Show HN: Berean Labs – Free AI-powered penetration testing for web apps
Berean Labs open-source autonomous AI penetration testing tool for detecting client-side vulnerabilities, exposed secrets, and web app misconfigurations.
2/20/2026
Show HN: SQL-tap now has a browser-based Web UI for real-time SQL monitoring
SQL-tap: transparent SQL proxy with new browser-based Web UI for real-time query inspection, EXPLAIN, filtering, and analysis.
2/20/2026
California introduces a bill (AB-2047) that will limit the use of 3D printers
California legislative bill on 3D printer firearm prevention technology, not AI-related.
2/20/2026
Theres no mainstream AI video editing tool?
User asks about AI video editing tools availability. Low-effort question without substantive content or research.