3/19/2026
Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models
Method for improving mathematical reasoning in smaller LLMs by integrating arithmetic learning with knowledge distillation and data augmentation.
3/19/2026
Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey
Survey of edge-cloud collaborative computing paradigms for distributed AI deployment, covering model optimization and LLM inference strategies.
3/19/2026
Optimization over Trained (and Sparse) Neural Networks: A Surrogate within a Surrogate
Framework for constraint learning using pruned neural networks as tractable surrogates in optimization problems.
3/19/2026
Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer
CIM-Explorer tool for optimizing binary and ternary neural networks on RRAM crossbar hardware architectures.
3/19/2026
A quantitative analysis of semantic information in deep representations of text and images
Information Imbalance metric for analyzing semantic information alignment in deep representations across text and image models.
3/19/2026
Statistical Inference for Online Algorithms
Methods for constructing confidence intervals and hypothesis tests for functionals derived from online/sequential algorithms with computational constraints.
3/19/2026
BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases
BiomedSQL benchmark for evaluating text-to-SQL systems on biomedical knowledge bases requiring implicit domain reasoning and scientific understanding.
3/19/2026
Code Roulette: How Prompt Variability Affects LLM Code Generation
Study on how prompt variability affects LLM code generation quality and functionality across different user backgrounds and expertise levels.
3/19/2026
Decadal sink-source shifts of forest aboveground carbon since 1988
Deep learning models integrated with satellite data to reconstruct global forest carbon dynamics from 1988-2021 with uncertainty quantification.
3/19/2026
Hebbian Physics Networks: A Self-Organizing Computational Architecture Based on Local Physical Laws
Hebbian Physics Networks: self-organizing computational architecture using plastic transport geometry for solving physical dynamics problems.
3/19/2026
From Street Form to Spatial Justice: Explaining Urban Exercise Inequality via a Triadic SHAP-Informed Framework
SHAP-based framework for analyzing urban exercise inequality using spatial theory and machine learning on Shenzhen street data.
3/19/2026
Robust estimation of heterogeneous treatment effects in randomized trials leveraging external data
QR-learner model for estimating conditional treatment effects in trials using external data.
3/19/2026
ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
ToolRegistry: protocol-agnostic tool management library for function-calling LLMs, addressing fragmentation in tool integration.
3/19/2026
Exact Generalisation Error Exposes Benchmarks Skew Graph Neural Networks Success (or Failure)
Analysis of GNN generalization error to explain performance variance and benchmark skew in graph neural networks.
3/19/2026
InPhyRe Discovers: Large Multimodal Models Struggle in Inductive Physical Reasoning
Benchmark study showing large multimodal models fail at inductive physical reasoning beyond training distribution.
3/19/2026
EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing
EdiVal-Agent framework for automated, fine-grained evaluation of multi-turn image editing using object-centric assessment.
3/19/2026
Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
Detection methods for data contamination in RL post-training phase of LLMs, addressing evaluation validity gap.
3/19/2026
On the identifiability of causal graphs with multiple environments
Causal discovery method using multi-environment data to achieve full causal graph identifiability with minimal environments.
3/19/2026
CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
CBF-RL integrates Control Barrier Functions into RL training to enforce safety constraints during policy learning.
3/19/2026
Learning Time-Varying Graphs from Incomplete Graph Signals
Unified optimization framework for jointly inferring time-varying network topologies and imputing missing graph signal data.
3/19/2026
Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models
Neighbor GRPO extends Group Relative Policy Optimization to flow matching models with contrastive ODE-based approach for generative model alignment.
3/19/2026
Representation-Aware Unlearning via Activation Signatures: From Suppression to Knowledge-Signature Erasure
Knowledge Immunization Framework for selective knowledge erasure from LLMs via representation-aware activation signatures, addressing GDPR and safety.
3/19/2026
Learning the Intrinsic Dimensionality of Fermi-Pasta-Ulam-Tsingou Trajectories: A Nonlinear Approach using a Deep Autoencoder Model
Deep autoencoder applied to FPUT trajectories to infer intrinsic dimensionality in weakly nonlinear regime.
3/19/2026
Lyapunov Constrained Soft Actor-Critic (LC-SAC) using Koopman Operator Theory for Quadrotor Trajectory Tracking
Reinforcement learning approach combining Lyapunov stability constraints with soft actor-critic for safe quadrotor control.
3/19/2026
Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
Study demonstrating reward-free backdoor attacks on RL agents through compromised simulators.
3/19/2026
PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification
Knowledge distillation framework for fine-grained visual classification using vision-language models with prompt-aware calibration.
3/19/2026
Unlearnable phases of matter
Theoretical study identifying phases of matter computationally hard to learn with autoregressive neural networks.
3/19/2026
GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
Learnable Gaussian sampling method for inference-time scaling in latent reasoning models to improve reasoning path generation.
3/19/2026
Dual Space Preconditioning for Gradient Descent in the Overparameterized Regime
Analysis of gradient descent convergence with dual space preconditioners in overparameterized linear models.
3/19/2026
Ethical Fairness without Demographics in Human-Centered AI
Method for achieving fairness in AI systems without demographic attributes for human-centered applications.
3/19/2026
Event-Driven Video Generation
Event-driven approach to text-to-video generation that models discrete interactions and causality rather than frame-by-frame updates.
3/19/2026
REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning
Method for fine-tuning diffusion policies with reinforcement learning for humanoid robot loco-manipulation tasks.
3/19/2026
Solving physics-constrained inverse problems with conditional flow matching
Conditional flow matching framework for solving physics-constrained Bayesian inverse problems without explicit likelihood evaluation.
3/19/2026
ASAP: Attention-Shift-Aware Pruning for Efficient LVLM Inference
Pruning method for efficient large vision-language model inference by exploiting attention patterns and addressing token redundancy.
3/19/2026
Online Learning for Supervisory Switching Control
Online learning approach for supervisory switching control of partially-observed linear dynamical systems with finite-time performance bounds.
3/19/2026
Halfway to 3D: Ensembling 2.5D and 3D Models for Robust COVID-19 CT Diagnosis
Deep learning framework combining 2.5D and 3D representations for COVID-19 detection from CT scans.
3/19/2026
Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods
Training-free method for detecting AI-generated videos using spatial-temporal likelihood analysis without supervised training.
3/19/2026
I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning
Framework for aggregating noisy heterogeneous evidence in probabilistic reasoning tasks with explicit uncertainty quantification.
3/19/2026
Theoretical Foundations of Latent Posterior Factors: Formal Guarantees for Multi-Evidence Reasoning
Theoretical framework for aggregating multiple evidence sources in probabilistic prediction with formal guarantees for multi-evidence reasoning.
3/19/2026
Neural Pushforward Samplers for the Fokker-Planck Equation on Embedded Riemannian Manifolds
Machine learning method extending weak adversarial neural pushforward to solve Fokker-Planck equations on Riemannian manifolds.
3/19/2026
k8s multi tenancy: its a cluster f*ck
Kubernetes multi-tenancy challenges with AI agents requiring ephemeral environments. Infrastructure scaling issues.
3/19/2026
The Flawed Ephemeral Software Hypothesis
Analysis arguing software won't become disposable despite AI coding agents, critiquing concepts like 'vibe coding' and ephemeral apps.
3/19/2026
South Korea's SDT opens Quantum-AI data center
South Korea's SDT opens first commercial quantum-AI hybrid data center in Seoul with 20-qubit Kreo quantum computer and Nvidia DGX B200 integration.
3/19/2026
Show HN: I created a free tool to analysis your old blog posts for suggestions
Free SEO tool for analyzing blog posts with section-by-section content refresh recommendations.
3/19/2026
Violations of LLM Review Policies
ICML 2026 policy document on violations of LLM review policies and maintaining scientific integrity in peer review.
3/19/2026
Scheduled: Open-Source Calendly, but AI
Scheduled: Open-source AI agent integrated with Gmail that autonomously reads meeting request emails, checks calendar availability, and drafts proposed times.
3/19/2026
RQ-180 Stealth Drone Appears to Have Made an Emergency Landing at Greek Air Base
Military news article about RQ-180 stealth drone emergency landing at Greek air base.
3/19/2026
Show HN: ATO – a GUI to see and fix what your LLM agents configured
ATO: GUI control panel managing multiple LLM agents (Claude Code, Codex, OpenClaw, Hermes) with workflow orchestration and MCP integration.
3/19/2026
AI pilot program in LA County courts will help judges craft rulings
LA County courts pilot AI tool (Learned Hand) to summarize legal motions and draft rulings based on judge writing styles.
3/19/2026
The Agentic Organization
Conceptual framework on how AI agents transform organizational structure and decision-making beyond efficiency gains.