AI News

HybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research Agents (arxiv.org)

Building Auditable AI Text Detectors with Sparse Autoencoders (arxiv.org)

Every Alarm Has a Cause: An Open Generator of Telecom Alarm Storms with Exact Root Causes, Bound to NORIA-O, RFC 8632 and TMF642 (arxiv.org)

MoEZip: Routing-Aware KV Cache Compression for Sparse Mixture-of-Experts LLMs (arxiv.org)

AQL-Lite: Enabling Efficient Knowledge Acquisition for Arabic LLMs via Data-Centric Continual Pretraining (arxiv.org)

TerraTransfer++: Demonstration-Free End-to-End Planner (arxiv.org)

SciFusion: Physics-Guided Compositional Diffusion for Multimodal 3D Scientific Image Generation (arxiv.org)

Graph Topology Meets Energy-Driven Pathfinding: Preserving Contextual Consistency in Retrieval-Augmented Generation (arxiv.org)

Asking a Multimodal LLM Whether Someone Fell: Zero-Shot Screening of Low-Resolution Thermal Video in a Laboratory and an Occupied Home (arxiv.org)

Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models (arxiv.org)

PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit (arxiv.org)

HiddenLens: A Multi-Layer LLM Framework for Detecting and Resolving Hidden Assumptions in Software Requirements (arxiv.org)

EgoHand: Monocular 3D Hand Reconstruction from Egocentric Video (arxiv.org)

Rethinking Sequence Compression with Test-time Regression (arxiv.org)

On the Token Collapse Phenomenon in Textual Graph Soft Prompting (arxiv.org)

Post-Hoc Feature Selection Layer for Neural Networks Interpretability (arxiv.org)

FaultGene: LLM-Assisted Fault-Augmented Test Generation for Hardware-in-the-Loop Validation of Autonomous Driving Systems (arxiv.org)

Every Part Has Its Role: Part-of-Speech Effects in LLM Post-Training (arxiv.org)

Broadband Mid-Wave Infrared Imaging Enabled by All-Silicon Hyperboloid Metalens (arxiv.org)

S-EDL: Eliciting Self-Evidence from Sequence Likelihoods for Semantic Calibration of LLMs (arxiv.org)

Robot Generalization Beyond Volume: The Diversity Path via Zero-Shot Capabilities (arxiv.org)

Is High Local Accuracy Enough? Geometric Consensus with Support-Adaptive Statistical Personalization for Federated Learning (arxiv.org)

nnInteractive Agent: General-Purpose AI Agents as 3D Image Annotators (arxiv.org)

When Forgotten Facts Return: Relearning-Aware Unlearning of Knowledge Graph Embeddings via Tangent Kernels (arxiv.org)

Doubly Robust Distributionally Robust Offline Contextual Pricing (arxiv.org)

MemoryTax: The Bitter Lesson of Agent Memory (arxiv.org)

Metamodel-Guided LLM Decoding for Consistent DSL Generation (arxiv.org)

SAKURA: Serving Attention Key-Value State Under Rate Adaptation for Private Image Editing on Phones (arxiv.org)

Retrieval Augmented Generation Compositionality (arxiv.org)

Ground-Truth-First Benchmarking of Reinforcement Learning via Converse Optimality: From Smooth, Fully Observed Systems to Non-Smooth or Partially Observed Tasks (arxiv.org)

OpenAttention: One Percent Is Enough with Tail Proxies (arxiv.org)

Building Presentation Intelligence for High-Quality Slide Generation (arxiv.org)

Tracing Subliminal Learning Through Pretraining (arxiv.org)

Joules-to-GDP: How Much Economic Value Do AI Systems Produce per Unit of Energy? (arxiv.org)

GIFT: Gradient Informed Filtering for Distillation Augmented Reasoning RL (arxiv.org)

Trace2World: Reconstructing App Worlds from Real Interaction Traces for Scalable GUI Agent Training (arxiv.org)

Gandalf: Flash Shall Not Die! Increasing Flash Storage Lifetime for KV Cache Offloading in LLM Serving (arxiv.org)

Toward Recursive Self-Improvement in Physical AI (arxiv.org)

Conflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement (arxiv.org)

Formalizing Cooperation and Competition: An AI-Assisted Mathematical Addendum to a 2018 Planning Thesis (arxiv.org)

FogTTA: Online Test-Time Adaptation for Robust Transformer-based Object Detection in Foggy Weather (arxiv.org)

An interpretable deep learning method for early hepatocellular carcinoma diagnosis on multiphase CT (arxiv.org)

One Pretrained Decision Model Is Enough for Training-Free Generalist Graph Anomaly Detection (arxiv.org)

Adaptive Deadline- and Energy-Aware Caching Algorithms in Dynamic Multi-UAV Edge Networks (arxiv.org)

Primal-Dual Representation Learning for Low-Rank Constrained MDPs (arxiv.org)

Visualizing and Interpreting Temporal Care Team Dynamics for Cancer Survival Risk Analysis (arxiv.org)

CulturalRiddles: A Multicultural Benchmark of Riddles (arxiv.org)

Overview of CHIP 2026 Shared Task 1: Patient-Specific Phenotype Concept Recognition in Full-Text Biomedical Literature (arxiv.org)

From AI-Free Gates to AI-First Work: How Engineering Students in India Navigate University Education and Campus Placements Without AI Guidelines (arxiv.org)

GRAFT: Restoring the Missing Sampling Interface in Continuous Diffusion Language Models (arxiv.org)