3/16/2026
Integration of TinyML and LargeML: A Survey of 6G and Beyond
Survey on integrating TinyML and LargeML for 6G networks, covering deep learning applications in mobile systems, autonomous vehicles, and smart services.
3/16/2026
Token Distillation: Attention-aware Input Embeddings For New Tokens
Attention-aware embedding initialization method for new tokens in LLMs without expensive retraining, addressing vocabulary limitations in specialized domains.
3/16/2026
Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection
Conditional marked point processes for reliable object detection uncertainty quantification, addressing miscalibrated confidence scores in neural networks.
3/16/2026
From Video to EEG: Adapting Joint Embedding Predictive Architecture to Uncover Saptiotemporal Dynamics in Brain Signal Analysis
Self-supervised learning approach adapting joint embedding architecture from video to EEG signals for brain activity analysis with limited labeled data.
3/16/2026
Quantum-Informed Machine Learning for Predicting Spatiotemporal Chaos with Practical Quantum Advantage
Quantum-informed ML framework combining quantum generative models with classical predictors for long-term spatiotemporal chaos prediction.
3/16/2026
Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach
Supervised fine-tuning method to align LLM agents with rational and moral preferences in strategic economic games, addressing systematic behavioral deviations.
3/16/2026
SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object Tokens
Object-centric representations for visual RL policies using dynamic tokens to improve generalization under visual condition changes without fixed-size slots.
3/16/2026
On the (In)Security of Loading Machine Learning Models
Security evaluation of ML model sharing frameworks and hubs, assessing vulnerabilities in loading shared models and security awareness gaps among practitioners.
3/16/2026
Neural-Quantum-States Impurity Solver for Quantum Embedding Problems
Neural quantum states impurity solver for quantum embedding problems. Graph transformer-based NQS for solving Hamiltonians in quantum chemistry.
3/16/2026
Dynamic Aware: Adaptive Multi-Mode Out-of-Distribution Detection for Trajectory Prediction in Autonomous Vehicles
Dynamic Aware: out-of-distribution detection for trajectory prediction in autonomous vehicles. Adaptive multi-mode approach for distribution shift in AVs.
3/16/2026
AutoClimDS: Climate Data Science Agentic AI -- A Knowledge Graph is All You Need
AutoClimDS: agentic AI system for climate data science. Knowledge graph-based workflows for discovering climate patterns from fragmented data sources.
3/16/2026
From Formal Language Theory to Statistical Learning: Finite Observability of Subregular Languages
Formal language theory applied to statistical learning. Proves subregular language classes are linearly separable with simple models.
3/16/2026
Scaling Generalist Data-Analytic Agents
DataMind: scalable data-analytic AI agents for automated discovery. Open-source agent framework handling diverse-format data files and multi-step reasoning.
3/16/2026
HoneyBee: Data Recipes for Vision-Language Reasoners
HoneyBee: data curation approaches for vision-language reasoning datasets. Analyzes impact of context, content, and format on VLM reasoning capabilities.
3/16/2026
CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
CBF-RL: integrates control barrier functions into reinforcement learning training. Enforces dynamic safety constraints during RL policy training, not just inference.
3/16/2026
RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation
RobotArena ∞: scalable robot benchmarking via real-to-sim translation. Enables rigorous evaluation of robot policies across diverse tasks and environments.
3/16/2026
Verifying LLM Inference to Detect Model Weight Exfiltration
Verifying LLM inference to detect model weight exfiltration via steganography. Defends inference servers against model theft and anomalous behavior.
3/16/2026
AnatomiX, an Anatomy-Aware Grounded Multimodal Large Language Model for Chest X-Ray Interpretation
AnatomiX: anatomy-aware multimodal LLM for chest X-ray interpretation. Improves spatial reasoning and anatomical understanding in medical imaging.
3/16/2026
FARM: Few-shot Adaptive Malware Family Classification under Concept Drift
FARM framework for malware family classification under concept drift. Uses triplet autoencoder for few-shot adaptation to covariate and label drift.
3/16/2026
LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
LatentChem: latent reasoning interface for chemical LLMs. Decouples chemical computation from discrete tokens to improve efficiency and performance in chemical reasoning.
3/16/2026
Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference
Pyramid MoA: probabilistic framework for cost-optimized LLM inference via cascading and routing. Balances inference cost and reasoning capability for large language models.
3/16/2026
IROSA: Interactive Robot Skill Adaptation using Natural Language
IROSA: framework combining foundation models with imitation learning for robot skill adaptation via natural language. LLM application to robotics.
3/16/2026
Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models
Disentangled Safety Hypothesis: mechanistic study of LLM safety showing decoupling between harmfulness detection and refusal. ML interpretability research.
3/16/2026
Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
Benchmark evaluating frontier AI models on multi-step cyber attack scenarios. Agent capability measurement across extended action sequences.
3/16/2026
One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queries
Agentic framework for multimodal query processing with adaptive tool orchestration across text/image/audio/video. Research on agent coordination and tool selection.
3/16/2026
Proof-Carrying Materials: Falsifiable Safety Certificates for Machine-Learned Interatomic Potentials
Proof-Carrying Materials: falsifiable safety certificates for machine-learned interatomic potentials. ML research on reliability guarantees for scientific models.
3/16/2026
Show HN: Run the popular LLM-Course tutorials on HyperAI
HyperAI provides browser-based notebooks for running LLM-Course tutorials covering LLM fundamentals and production applications.
3/16/2026
DeepSteve: A hackable multi-terminal for AI coding agents
DeepSteve: hackable multi-terminal environment for AI coding agents with customizable interfaces.
3/16/2026
Open Source tool to detect On-Call Burnout from incident response patterns
On-Call Health: open-source tool detecting burnout patterns in incident responders using data from PagerDuty, GitHub, and other platforms.
3/16/2026
Rust Project Perspectives on AI
Rust project documentation on community perspectives regarding AI use policy and governance in open-source development.
3/16/2026
Ask HN: If AI makes your devs super productive, why layoff?
Hacker News discussion questioning company layoff rationale when AI increases developer productivity.
3/16/2026
Show HN: CastLoom Pro – Turn podcasts into a personal knowledge base
Desktop app converting podcasts into searchable knowledge base with transcription, translation, and archival capabilities.
3/16/2026
Training-Free Infinite Video Generation via Evolving Memory Tokens
Training-free infinite video generation using evolving memory tokens via MemRoPE without KV cache limitations.
3/16/2026
Getting the most out of Claude agent teams
Framework for effective multi-agent teams treating them as organizational units rather than parallel single agents for improved collaboration outcomes.
3/16/2026
Show HN: IdeaCred – automated scoring for GitHub repos
IdeaCred: tool scoring GitHub repositories using LLM analysis and GitHub API metrics across innovation, craft, traction, and scope.
3/16/2026
Show HN: Regrada – The CI gate for LLM behavior
Testing framework for LLM applications using call interception and behavior comparison. CI gates for prompt changes with baseline drift detection.
3/16/2026
Jsse: Agent-coded JavaScript engine in Rust passing 99.96% of test262
Jsse: JavaScript engine written in Rust entirely by AI agents, achieving 99.96% test262 compliance without manual code contributions.
3/16/2026
Your AI Agent Is Building Shadow IT and Nobody Noticed
Enterprise AI coding agents create unauthorized shadow IT systems, raising organizational governance concerns as autonomous tools bypass approval processes.
3/16/2026
Gstack-auto: automated gstack builds with parallelized runs
Gstack-auto tool for automated, parallelized builds using AI coding agents iteratively to refine software through testing and bugfixes rather than single prompts.
3/16/2026
Show HN: AutoBlogWriter – drop-in blog automation SDK for Next.js and React
SDK for Next.js/React blog automation with AI-assisted integration. Generates blog metadata, schema, sitemaps, and scheduling via agent workflow.
3/16/2026
Show HN: Clsh – Real terminal on your phone (works with Claude Code)
Terminal emulator for iOS enabling remote agent supervision. Addresses Claude Code workflow by fixing mobile terminal UX limitations.
3/16/2026
VibeSDK: I ported all features of Pydantic AI to TypeScript in 5hrs
TypeScript port of Pydantic AI framework. Agent SDK with 50+ LLM provider support via Vercel AI SDK. Open-source with full documentation.
3/16/2026
"How I write software with LLMs"
Personal essay on using LLMs for software development, emphasizing how LLMs enable creative making and shift focus from programming mechanics to creative output.
3/16/2026
Show HN: Voxlert – SHODAN and the StarCraft Adjutant narrate my agent sessions
Voxlert is an open-source tool using LLM and TTS to give distinct character voices to concurrent Claude/Codex agent sessions for better notification tracking.
3/16/2026
Ask HN: How is your team collaborating while working with coding agents?
HN discussion about team collaboration practices when using AI coding agents like Claude Code and Codex, integration with project management tools.
3/16/2026
Nan Da on Ethics of AIs as Engines of Transductive Inference
Essay on transductive inference theory applied to AI systems, exploring how next-word prediction relates to broader AI reasoning tasks.
3/16/2026
What Is Agentic Engineering?
Overview of agentic engineering practices for developing software with AI coding agents like Claude Code and Gemini CLI, including definitions and patterns.
3/16/2026
An experiment to use GitHub Actions as a control plane for a PaaS
Self-hosted PaaS platform using GitHub Actions as control plane for deploying multiple applications on single Debian server.
3/16/2026
The First Open-Source Agentic AI Physicist [video]
Reference to open-source agentic AI physicist project (video format, minimal content provided).
3/16/2026
Why Codex Security Doesn’t Include a SAST Report
Codex Security: AI agent for code security that analyzes repository architecture and trust boundaries before validating findings with humans.