AI News

Rethinking Learnability in Offline Data-driven Optimization (arxiv.org)

Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning (arxiv.org)

Edge-Girth as a Structural Edge Feature for Graph Neural Networks (arxiv.org)

Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search (arxiv.org)

CATeye: Coupled Attribute-Topology Invariance Learning for Voucher Abuse Detection (arxiv.org)

Towards a Reliable and Practical Eval Pipeline (arxiv.org)

StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability? (arxiv.org)

Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment (arxiv.org)

When Features Become Instances: Inverted Contrastive Learning for Unsupervised Feature Selection (arxiv.org)

DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory (arxiv.org)

Automated Tree Knowledge Graph Construction using Ontology Expansion and Retrieval from Vietnamese History Textbooks (arxiv.org)

S^3martCirc: Self-supervised Smart Circuit Discovery (arxiv.org)

ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents (arxiv.org)

Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs (arxiv.org)

Agentic Empirical Asset Pricing: Methodological Foundations (arxiv.org)

SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification (arxiv.org)

A Closed-Loop Evaluation of Capability Loss and Recovery in Compressed Driving Policies (arxiv.org)

Towards Agentic Cloud Engineering: Graph and Loop Engineering with a Zero-Trust Agent Harness (arxiv.org)

ChatDev 2.0: A No-Code Multi-Agent Platform for Developing Everything (arxiv.org)

Value Over Language Model: Detecting Original Contribution in Writing (arxiv.org)

Triple-Bottom-Line Sustainability of Language Models for Edge AI: A Comparison Between SLMs and Quantized LLMs (arxiv.org)

CHARM: Character Hallucination for Multicultural Role Play Benchmark (arxiv.org)

Scalable Rao-Blackwellized Online Planning for High-Dimensional POMDPs (arxiv.org)

Probing Factual Knowledge Transfer with Training Data Interventions (arxiv.org)

HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives (arxiv.org)

Iterative GRPO: Batch-Online Policy Iteration for Multi-Turn RL via Single-Turn RLHF (arxiv.org)

EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents (arxiv.org)

Some Emotions Run Deeper: Layer-wise Probing and Causal Intervention in Large Language Models (arxiv.org)

MutMem-V2: Cryptographically Authorized Mutation in Persistent Agent Memory Portable Verification and Reproducible Evidence (arxiv.org)

TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models (arxiv.org)

One Prompt Is Enough: Watermark Laundering Through Foundation Image Models (arxiv.org)

Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling (arxiv.org)

PopPert: Population-level Joint-Distribution Modeling for Single-Cell Perturbation Prediction (arxiv.org)

Stress Testing Unlearning Algorithms (arxiv.org)

TempCloze: Can Video-LLMs Identify the Missing Middle? (arxiv.org)

GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions (arxiv.org)

When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning (arxiv.org)

Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching (arxiv.org)

WebFPGA (webfpga.io)

LZ Experiment Sees Surprising Result In Search For Dark Matter (science.slashdot.org)

Atlas by World Labs (www.producthunt.com)

Why the “One Giant Table” CDP is Dead: Building a Scalable Hub-and-Spoke Customer 360 in BigQuery (medium.com)

Centralized Google API traffic Inspection with a Network Virtual Appliance (NVA) (medium.com)

Your Agent Doesn’t Know How to Wait (medium.com)

Evaluating AI models with SQL in Google Cloud databases (medium.com)

Human, Machine, Agent: The Three Identity Kinds on Google Cloud (medium.com)

Disaggregated Serving on B200s: 5.9x goodput, and what it costs (medium.com)

Agent skills, Part 2: Image generation (medium.com)

Take your AI Harness with you with Antigravity Remote Control (medium.com)

OSS — Kubernetes on GCE , DRA Driver for NVIDIA GPUs, DRANET (OSS) and NCCL test — AI Infra (medium.com)