AI News — Latest Developments & Breakthroughs

ArXiv cs.AI 📄 Paper 12h ago

Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification

arXiv:2603.26348v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong multimodal reasoning performance, yet we identify a re

ArXiv cs.AI 📄 Paper 12h ago

Generative Score Inference for Multimodal Data

arXiv:2603.26349v1 Announce Type: cross Abstract: Accurate uncertainty quantification is crucial for making reliable decisions in various supervised learning sc

ArXiv cs.AI 📄 Paper 12h ago

Automated near-term quantum algorithm discovery for molecular ground states

arXiv:2603.26359v1 Announce Type: cross Abstract: Designing quantum algorithms is a complex and counterintuitive task, making it an ideal candidate for AI-drive

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 12h ago

Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards

arXiv:2603.26378v1 Announce Type: cross Abstract: Generative modeling has become a central paradigm in protein research, extending machine learning beyond struc

ArXiv cs.AI 📄 Paper 12h ago

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

arXiv:2603.26410v1 Announce Type: cross Abstract: Extended-thinking models expose a second text-generation channel ("thinking tokens") alongside the user-visibl

ArXiv cs.AI 📄 Paper 12h ago

KMM-CP: Practical Conformal Prediction under Covariate Shift via Selective Kernel Mean Matching

arXiv:2603.26415v1 Announce Type: cross Abstract: Uncertainty quantification is essential for deploying machine learning models in high-stakes domains such as s

ArXiv cs.AI 📄 Paper 12h ago

CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities

arXiv:2603.26425v1 Announce Type: cross Abstract: Recent research on vision backbone architectures has predominantly focused on optimizing efficiency for hardwa

ArXiv cs.AI 📄 Paper 12h ago

Can AI Models Direct Each Other? Organizational Structure as a Probe into Training Limitations

arXiv:2603.26458v1 Announce Type: cross Abstract: Can an expensive AI model effectively direct a cheap one to solve software engineering tasks? We study this qu

ArXiv cs.AI 📄 Paper 12h ago

Neuro-Symbolic Process Anomaly Detection

arXiv:2603.26461v1 Announce Type: cross Abstract: Process anomaly detection is an important application of process mining for identifying deviations from the no

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 12h ago

A Boltzmann-machine-enhanced Transformer For DNA Sequence Classification

arXiv:2603.26465v1 Announce Type: cross Abstract: DNA sequence classification requires not only high predictive accuracy but also the ability to uncover latent

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 12h ago

UNIFERENCE: A Discrete Event Simulation Framework for Developing Distributed AI Models

arXiv:2603.26469v1 Announce Type: cross Abstract: Developing and evaluating distributed inference algorithms remains difficult due to the lack of standardized t

ArXiv cs.AI 📄 Paper 12h ago

Foundation Model for Cardiac Time Series via Masked Latent Attention

arXiv:2603.26475v1 Announce Type: cross Abstract: Electrocardiograms (ECGs) are among the most widely available clinical signals and play a central role in card

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 12h ago

Rocks, Pebbles and Sand: Modality-aware Scheduling for Multimodal Large Language Model Inference

arXiv:2603.26498v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling richer in

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 12h ago

AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese

arXiv:2603.26511v1 Announce Type: cross Abstract: Despite rapid progress in open large language models (LLMs), European Portuguese (pt-PT) remains underrepresen

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 12h ago

JAL-Turn: Joint Acoustic-Linguistic Modeling for Real-Time and Robust Turn-Taking Detection in Full-Duplex Spoken Dialogue Systems

arXiv:2603.26515v1 Announce Type: cross Abstract: Despite recent advances, efficient and robust turn-taking detection remains a significant challenge in industr

ArXiv cs.AI 📄 Paper 12h ago

ALBA: A European Portuguese Benchmark for Evaluating Language and Linguistic Dimensions in Generative LLMs

arXiv:2603.26516v1 Announce Type: cross Abstract: As Large Language Models (LLMs) expand across multilingual domains, evaluating their performance in under-repr

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 12h ago

How Open Must Language Models be to Enable Reliable Scientific Inference?

arXiv:2603.26539v1 Announce Type: cross Abstract: How does the extent to which a model is open or closed impact the scientific inferences that can be drawn from

ArXiv cs.AI 📄 Paper 12h ago

The Multi-AMR Buffer Storage, Retrieval, and Reshuffling Problem: Exact and Heuristic Approaches

arXiv:2603.26542v1 Announce Type: cross Abstract: Buffer zones are essential in production systems to decouple sequential processes. In dense floor storage envi

ArXiv cs.AI 👁️ Computer Vision 📄 Paper ⚡ AI Lesson 12h 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 📄 Paper 12h ago

When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models

arXiv:2603.26556v1 Announce Type: cross Abstract: Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising

ArXiv cs.AI 📄 Paper 12h ago

Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering

arXiv:2603.26567v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown impressive capabilities across software engineering tasks, including q

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 12h 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 12h 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 📄 Paper 12h ago

Sustainability Is Not Linear: Quantifying Performance, Energy, and Privacy Trade-offs in On-Device Intelligence

arXiv:2603.26603v1 Announce Type: cross Abstract: The migration of Large Language Models (LLMs) from cloud clusters to edge devices promises enhanced privacy an

📰 AI News