AI News — Latest Developments & Breakthroughs

ArXiv cs.AI 👁️ Computer Vision 📄 Paper ⚡ AI Lesson 9h ago

Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones

arXiv:2603.26551v1 Announce Type: cross Abstract: Vision backbone networks play a central role in modern computer vision. Enhancing their efficiency directly be

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

Generation Is Compression: Zero-Shot Video Coding via Stochastic Rectified Flow

arXiv:2603.26571v1 Announce Type: cross Abstract: Existing generative video compression methods use generative models only as post-hoc reconstruction modules at

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 9h ago

Evaluating Interactive 2D Visualization as a Sample Selection Strategy for Biomedical Time-Series Data Annotation

arXiv:2603.26592v1 Announce Type: cross Abstract: Reliable machine-learning models in biomedical settings depend on accurate labels, yet annotating biomedical t

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

Make Geometry Matter for Spatial Reasoning

arXiv:2603.26639v1 Announce Type: cross Abstract: Empowered by large-scale training, vision-language models (VLMs) achieve strong image and video understanding,

ArXiv cs.AI 👁️ Computer Vision 📄 Paper ⚡ AI Lesson 9h ago

PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning

arXiv:2603.26653v1 Announce Type: cross Abstract: We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric vide

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

Scale-Adaptive Balancing of Exploration and Exploitation in Classical Planning

arXiv:2305.09840v4 Announce Type: replace Abstract: Balancing exploration and exploitation has been an important problem in both game tree search and automated

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 9h ago

Extreme Value Monte Carlo Tree Search for Classical Planning

arXiv:2405.18248v3 Announce Type: replace Abstract: Despite being successful in board games and reinforcement learning (RL), Monte Carlo Tree Search (MCTS) comb

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

ReMe: Scaffolding Personalized Cognitive Training via Controllable LLM-Mediated Conversations

arXiv:2410.19733v2 Announce Type: replace Abstract: Global aging calls for scalable and engaging cognitive interventions. Computerized cognitive training (CCT)

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

ProbGuard: Probabilistic Runtime Monitoring for LLM Agent Safety

arXiv:2508.00500v3 Announce Type: replace Abstract: Large Language Model (LLM) agents increasingly operate across domains such as robotics, virtual assistants,

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

Humanline: Online Alignment as Perceptual Loss

arXiv:2509.24207v2 Announce Type: replace Abstract: Online alignment (e.g., GRPO) is generally more performant than offline alignment (e.g., DPO) -- but why? Dr

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens

arXiv:2510.08222v2 Announce Type: replace Abstract: Due to their inherent complexity, reasoning tasks have long been regarded as rigorous benchmarks for assessi

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

Shared Spatial Memory Through Predictive Coding

arXiv:2511.04235v4 Announce Type: replace Abstract: Constructing a consistent shared spatial memory is a critical challenge in multi-agent systems, where partia

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design Optimization

arXiv:2511.19669v2 Announce Type: replace Abstract: Conventional AI-driven AMS design automation algorithms remain constrained by their reliance on high-quality

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

Before We Trust Them: Decision-Making Failures in Navigation of Foundation Models

arXiv:2601.05529v4 Announce Type: replace Abstract: High success rates on navigation-related tasks do not necessarily translate into reliable decision making by

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation

arXiv:2601.08323v3 Announce Type: replace Abstract: Equipping agents with memory is essential for solving real-world long-horizon problems. However, most existi

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay

arXiv:2603.11601v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) excel at describing visual scenes, yet struggle to translate perception into p

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 9h ago

Draft-and-Prune: Improving the Reliability of Auto-formalization for Logical Reasoning

arXiv:2603.17233v2 Announce Type: replace Abstract: Auto-formalization (AF) translates natural-language reasoning problems into solver-executable programs, enab

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

Governance-Aware Vector Subscriptions for Multi-Agent Knowledge Ecosystems

arXiv:2603.20833v2 Announce Type: replace Abstract: As AI agent ecosystems grow, agents need mechanisms to monitor relevant knowledge in real time. Semantic pub

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly

arXiv:2405.00181v3 Announce Type: replace-cross Abstract: Video anomaly understanding (VAU) aims to automatically comprehend unusual occurrences in videos, ther

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 9h ago

Complexity-Aware Deep Symbolic Regression with Robust Risk-Seeking Policy Gradients

arXiv:2406.06751v3 Announce Type: replace-cross Abstract: We propose a novel deep symbolic regression approach to enhance the robustness and interpretability of

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

CGRA4ML: A Hardware/Software Framework to Implement Neural Networks for Scientific Edge Computing

arXiv:2408.15561v4 Announce Type: replace-cross Abstract: The scientific community increasingly relies on machine learning (ML) for near-sensor processing, leve

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 9h ago

INSIGHT: Enhancing Autonomous Driving Safety through Vision-Language Models on Context-Aware Hazard Detection and Edge Case Evaluation

arXiv:2502.00262v4 Announce Type: replace-cross Abstract: Autonomous driving systems face significant challenges in handling unpredictable edge-case scenarios,

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 9h ago

Biogeochemistry-Informed Neural Network (BINN) for Improving Accuracy of Model Prediction and Scientific Understanding of Soil Organic Carbon

arXiv:2502.00672v3 Announce Type: replace-cross Abstract: The increasing availability of large-scale observational data and the rapid development of artificial

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 9h ago

Hierarchical and Multimodal Data for Daily Activity Understanding

arXiv:2504.17696v4 Announce Type: replace-cross Abstract: Daily Activity Recordings for Artificial Intelligence (DARai, pronounced "Dahr-ree") is a multimodal,

⚡ AI-Lesson Articles