📰 AI News

10,465 articles · Updated every 3 hours

arXiv:2604.02674v1 Announce Type: cross Abstract: Large Language Model (LLM) multi-agent systems are increasingly deployed as interacting agent societies, yet s

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

Eligibility-Aware Evidence Synthesis: An Agentic Framework for Clinical Trial Meta-Analysis

arXiv:2604.02678v1 Announce Type: cross Abstract: Clinical evidence synthesis requires identifying relevant trials from large registries and aggregating results

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

Finding Belief Geometries with Sparse Autoencoders

arXiv:2604.02685v1 Announce Type: cross Abstract: Understanding the geometric structure of internal representations is a central goal of mechanistic interpretab

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

arXiv:2604.02686v1 Announce Type: cross Abstract: Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLH

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs

arXiv:2604.02689v1 Announce Type: cross Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have expanded reasoning capabilities into 3D domai

ArXiv cs.AI 🛡️ AI Safety & Ethics 📄 Paper ⚡ AI Lesson 5d ago

DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning

arXiv:2604.02694v1 Announce Type: cross Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing ma

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints

arXiv:2604.02699v1 Announce Type: cross Abstract: A previous study reported that E-Prime (English without the verb "to be") selectively altered reasoning in lan

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy

arXiv:2604.02709v1 Announce Type: cross Abstract: The formal reasoning capabilities of LLMs are crucial for advancing automated software engineering. However, e

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

V2X-QA: A Comprehensive Reasoning Dataset and Benchmark for Multimodal Large Language Models in Autonomous Driving Across Ego, Infrastructure, and Cooperative Views

arXiv:2604.02710v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for autonomous driving, yet existing benc

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications

arXiv:2604.02719v1 Announce Type: cross Abstract: We introduce MOMO, the first multi-sensor foundation model for Mars remote sensing. MOMO uses model merge to i

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

IndustryCode: A Benchmark for Industry Code Generation

arXiv:2604.02729v1 Announce Type: cross Abstract: Code generation and comprehension by Large Language Models (LLMs) have emerged as core drivers of industrial i

ArXiv cs.AI 🤖 AI Agents & Automation 📄 Paper ⚡ AI Lesson 5d ago

Cross Event Detection and Topic Evolution Mining in cross events for Man Made Disasters in Social Media Streams

arXiv:2604.02740v1 Announce Type: cross Abstract: Social media is widely used to share information globally and it also aids to gain attention from the world. W

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs

arXiv:2604.02766v1 Announce Type: cross Abstract: Modern LLMs inherit strong priors from web-scale pretraining, which can limit the headroom of post-training da

ArXiv cs.AI 🤖 AI Agents & Automation 📄 Paper ⚡ AI Lesson 5d ago

SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems

arXiv:2604.02767v1 Announce Type: cross Abstract: When Agent A delegates to Agent B, which invokes Tool C on behalf of User X, no existing framework can answer:

ArXiv cs.AI 🤖 AI Agents & Automation 📄 Paper ⚡ AI Lesson 5d ago

Disrupting Cognitive Passivity: Rethinking AI-Assisted Data Literacy through Cognitive Alignment

arXiv:2604.02783v1 Announce Type: cross Abstract: AI chatbots are increasingly stepping into roles as collaborators or teachers in analyzing, visualizing, and r

ArXiv cs.AI 💻 AI-Assisted Coding 📄 Paper ⚡ AI Lesson 5d ago

LumaFlux: Lifting 8-Bit Worlds to HDR Reality with Physically-Guided Diffusion Transformers

arXiv:2604.02787v1 Announce Type: cross Abstract: The rapid adoption of HDR-capable devices has created a pressing need to convert the 8-bit Standard Dynamic Ra

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks

arXiv:2604.02795v1 Announce Type: cross Abstract: Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Model

ArXiv cs.AI 👁️ Computer Vision 📄 Paper ⚡ AI Lesson 5d ago

PaveBench: A Versatile Benchmark for Pavement Distress Perception and Interactive Vision-Language Analysis

arXiv:2604.02804v1 Announce Type: cross Abstract: Pavement condition assessment is essential for road safety and maintenance. Existing research has made signifi

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

ChatSVA: Bridging SVA Generation for Hardware Verification via Task-Specific LLMs

arXiv:2604.02811v1 Announce Type: cross Abstract: Functional verification consumes over 50% of the IC development lifecycle, where SystemVerilog Assertions (SVA

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models

arXiv:2604.02816v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong reasoning ability, but their high computational and

ArXiv cs.AI 👁️ Computer Vision 📄 Paper ⚡ AI Lesson 5d ago

NavCrafter: Exploring 3D Scenes from a Single Image

arXiv:2604.02828v1 Announce Type: cross Abstract: Creating flexible 3D scenes from a single image is vital when direct 3D data acquisition is costly or impracti

ArXiv cs.AI 📄 Paper 5d ago

Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis

arXiv:2604.02837v1 Announce Type: cross Abstract: Agent Skills is an emerging open standard that defines a modular, filesystem-based packaging format enabling L

ArXiv cs.AI 🛠️ AI Tools & Apps 📄 Paper ⚡ AI Lesson 5d ago

High-resolution probabilistic estimation of three-dimensional regional ocean dynamics from sparse surface observations

arXiv:2604.02850v1 Announce Type: cross Abstract: The ocean interior regulates Earth's climate but remains sparsely observed due to limited in situ measurements

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 5d ago

A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos

arXiv:2604.02860v1 Announce Type: cross Abstract: Temporal sentence grounding in videos (TSGV) aims to localize a temporal segment that semantically corresponds