3/30/2026
A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction
Investigation of channel-triggered backdoor attacks on semantic communication image reconstruction systems.
3/30/2026
Curved representational Bregman divergences and their applications
Mathematical framework defining curved Bregman divergences and their properties for statistical analysis.
3/30/2026
Diffusion Recommender Models and the Illusion of Progress: A Concerning Study of Reproducibility and a Conceptual Mismatch
Reproducibility study of diffusion-based recommender systems identifying methodological issues and limited actual progress.
3/30/2026
Is Supervised Learning Really That Different from Unsupervised?
Theoretical analysis showing supervised learning can be decomposed into unsupervised parameter selection plus label addition.
3/30/2026
Advancing Exchange Rate Forecasting: Leveraging Machine Learning and AI for Enhanced Accuracy in Global Financial Markets
LSTM-based machine learning models for USD/BDT exchange rate forecasting using historical financial data.
3/30/2026
StreamDiT: Real-Time Streaming Text-to-Video Generation
Real-time streaming text-to-video generation model using transformer-based diffusion for interactive applications.
3/30/2026
Out-of-Sight Embodied Agents: Multimodal Tracking, Sensor Fusion, and Trajectory Forecasting
Multimodal approach for trajectory prediction with sensor fusion and tracking for embodied agents in occluded scenarios.
3/30/2026
ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models
Benchmark (ORIC) examining vision-language model failures in object recognition under contextual incongruity scenarios.
3/30/2026
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Study on alternative training objectives for LLM fine-tuning beyond negative log likelihood to improve generalization.
3/30/2026
Multi-Dimensional Autoscaling of Stream Processing Services on Edge Devices
Multi-dimensional autoscaling platform for stream processing services on edge devices with limited resources.
3/30/2026
Altruistic Ride Sharing: A Framework for Fair and Sustainable Urban Mobility via Peer-to-Peer Incentives
Framework for decentralized peer-to-peer ride-sharing with altruistic incentive structures to reduce congestion and emissions.
3/30/2026
Bayesian Optimization on Networks
Bayesian optimization algorithms on metric graphs using Gaussian process surrogates for expensive black-box function evaluation.
3/30/2026
GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
GUI-AIMA alignment method for MLLMs to ground natural language instructions to UI regions, enabling computer-use agents via visual grounding.
3/30/2026
The Value of Personalized Recommendations: Evidence from Netflix
Econometric study of Netflix personalized recommendation value using discrete choice modeling, not ML development focused.
3/30/2026
PriVi: Towards A General-Purpose Video Model For Primate Behavior In The Wild
PriVi foundation model for primate behavior analysis in video, data-centric computer vision approach for non-human animal research.
3/30/2026
Architecting software monitors for control-flow anomaly detection through large language models and conformance checking
Framework combining LLMs and conformance checking for detecting control-flow anomalies in software monitoring, security application.
3/30/2026
WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
WorldMM memory-augmented video LLM agent for reasoning over hours-long videos with multimodal memory, addressing long-context understanding.
3/30/2026
Hear What Matters! Text-conditioned Selective Video-to-Audio Generation
SELVA model for text-conditioned selective video-to-audio generation, enabling fine-grained audio control from multimodal video input.
3/30/2026
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Nemotron-Cascade framework scaling reinforcement learning for general-purpose reasoning models, addressing heterogeneity in response lengths and verification latency.
3/30/2026
Uncovering Patterns of Brain Activity from EEG Data Consistently Associated with Cybersickness Using Neural Network Interpretability Maps
Neural network interpretability approach for identifying EEG patterns associated with cybersickness in VR, application of ML for neuroscience.
3/30/2026
ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation
Deep learning method for single image reflection separation using dual-stream architecture with cross-scale gated fusion, computer vision application.
3/30/2026
NRR-Phi: Text-to-State Mapping for Ambiguity Preservation in LLM Inference
Framework preserving ambiguity in LLM inference through non-collapsing state spaces, addressing premature semantic commitment in dialogue systems.
3/30/2026
Towards single-shot coherent imaging via overlap-free ptychography
Physics-based imaging technique extending ptychography to single-shot overlap-free coherent diffractive imaging, not AI/ML related.
3/30/2026
From Pixels to Patches: Pooling Strategies for Earth Embeddings
Analysis of pooling strategies for aggregating pixel-level embeddings from geospatial foundation models to patch-level representations.
3/30/2026
Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought
Diagnostic approach using entropy trajectory shapes to predict reasoning reliability in chain-of-thought LLM outputs, practical for uncertainty quantification.
3/30/2026
KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training
KALAVAI protocol predicting when independently trained specialist LLMs can be fused post-hoc, with quantitative formula for cooperative value estimation.
3/30/2026
MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG
MDKeyChunker pipeline for structure-aware document chunking and single-call LLM enrichment to improve RAG accuracy, addressing semantic fragmentation in retrieval.
3/30/2026
UniScale: Synergistic Entire Space Data and Model Scaling for Search Ranking
Scaling law research for search ranking systems examining synergy between data and model architecture, inspired by LLM advances with industrial applications.
3/30/2026
Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models
Side-channel attack framework exploiting dynamic high-resolution preprocessing in on-device vision-language models, revealing privacy risks from architectural design choices.
3/29/2026
There is No Spoon. A software engineers primer for demystified ML
ML primer for software engineers explaining machine learning systems design from first principles without mystification.
3/29/2026
I made Claude write a book about mayonnaise
AI-generated book about mayonnaise using Claude; humorous demonstration of LLM creative output.
3/29/2026
Show HN: SwarmDock – P2P marketplace where AI agents bid on tasks and earn USDC
P2P marketplace platform where AI agents compete for tasks and earn cryptocurrency rewards. Title only provided.
3/29/2026
Coding Agents Could Make Free Software Matter Again
Analysis of how coding agents could revitalize open-source software development. Title only provided.
3/29/2026
Kjell – Safely auto-approve AI agent shell commands through bash parsing
Bash parsing tool for safely auto-approving shell commands executed by AI agents. Title only provided.
3/29/2026
Mnemo – open-source memory and observability for AI agents (2 lines of code)
Open-source memory and observability tool for AI agents with minimal integration overhead. Title only provided.
3/29/2026
Claude Code runs Git reset –hard origin/main against project repo every 10 mins
Bug report: Claude Code automatically runs git reset --hard origin/main every 10 minutes, silently destroying uncommitted changes.
3/29/2026
A Year of Open Source Vulnerability Trends
Analysis of 2025 open-source vulnerability trends: reviewed advisories at 4-year low, malware advisories surged, CNA publishing grew.
3/29/2026
I'm an AI agent trying to run a real business. I've made $0. Here's my brain
Claude-based AI agent attempting to run Acrid Automation business with open-sourced operating system including boot file, skill framework, and memory persistence.
3/29/2026
What Is LLM Advertising? The New Ad Layer for AI-Powered Search
Analysis of advertising strategies within AI search tools and LLM conversations as alternative to traditional search ads.
3/29/2026
Uni feels so usless, I cant focus anymore
Personal post by first-year CS student questioning university value while pursuing research opportunities.
3/29/2026
Ask HN: How do you check what ChatGPT says about your product?
Discussion of testing LLM product awareness and descriptions across ChatGPT, Claude, Perplexity, and Gemini.
3/29/2026
QA Panda – Open-source AI QA engineer that tests web apps in a real browser
Open-source AI QA agent that tests web applications in real browsers, finds bugs, generates reports, and can delegate fixes to developer agents.
3/29/2026
US Air Force’s New Answer To Shahed Drones [video][13m]
Military hardware video about drone defense systems. Off-topic.
3/29/2026
Autogrind: Let your agent grind on your projects 24x7 fully autonomously
AutoGrind: AI agent skill enabling autonomous continuous work cycles on coding, ML, research, and design tasks without manual intervention.
3/29/2026
Attie: The Future of AI Should Serve People, Not Platforms
Essay on decentralized AI platforms and technology neutrality. Opinion piece without technical content.
3/29/2026
Show HN: Learn from AI Experts
Replit app using LLMs to summarize books for grounding AI in real expertise and discovery.
3/29/2026
Show HN: A war-strategy game played by AI agents
Open-source multiplayer game where teams of AI agents communicate, propose moves, and vote on strategy through emergent gameplay.
3/29/2026
Tell HN: Bug in Claude Code CLI is instantly draining usage plan quotas
Bug report: Claude Code CLI draining usage quotas 2-3x faster than normal since March 23, 2026, affecting multiple users.
3/29/2026
Ootils – An open source supply chain engine designed for AI agents (not humans)
Open-source supply chain decision engine built for AI agents with graph-based, deterministic, explainable API-first design.
3/29/2026
Show HN: Vocab extractor for language learners using Stanza and frequency ranks
Telegram bot using Stanza NLP pipeline and frequency ranks for vocabulary selection in language learning, outperforming GPT-4o-mini at lower levels.