AI News

Xiaomi-TabLDM: A Tabular Foundation Model Technical Report (arxiv.org)

STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation (arxiv.org)

Bioinfoysis Technical Report (arxiv.org)

Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations (arxiv.org)

Semantic Bayesian World Models (arxiv.org)

CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception (arxiv.org)

From Ordered Bernoulli Levels to Critical-Line Geometry: Integer Quantization, Bernoulli Residual Phase, and Prime-Power Spectra (arxiv.org)

SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation (arxiv.org)

Govern the Model, Not Only the Data: Storage, Circulation, and Learning in Creative AI (arxiv.org)

Transfiver: Human-AI Co-Inference through a Shared Editable State (arxiv.org)

DNative-Twin: Decision Graphs and Digital Twins for Reconstructable Agentic Decisions (arxiv.org)

Rethinking World Models for Safety-Critical Embodied Systems (arxiv.org)

SimSkill: A Lifelong Learning AI Agent for Autonomous Mastery of Traffic Simulation (arxiv.org)

Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation (arxiv.org)

Artificial Intelligence for Energy Optimization in Data Centers (arxiv.org)

Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study (arxiv.org)

Analysis of Prompt Engineering for Drug Toxicity Prediction (arxiv.org)

A computable representation of the physical laboratory enables verifiable workflows (arxiv.org)

KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents (arxiv.org)

The Attention Triangle in Audio-Video Models (arxiv.org)

LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL (arxiv.org)

LongCounsel-8: A Benchmark Suite for Longitudinal Depression Tracking from Multi-Session Counseling Dialogues (arxiv.org)

An Adversarial Zero-Shot Learning Approach for Anomaly Detection in Multivariate IoT Traffic Data (arxiv.org)

GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis (arxiv.org)

Dalek: A Constructive Agent Machine (arxiv.org)

Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation (arxiv.org)

NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease Diagnosis (arxiv.org)

CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning (arxiv.org)

Mixed Data Clustering Survey and Challenges (arxiv.org)

Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails (arxiv.org)

Mind the Gap: Robustness Risks in PII Detection Systems (arxiv.org)

A Two-Stage Forecasting System for CPU Workload Prediction in Private Clouds (arxiv.org)

Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree Coupling (arxiv.org)

Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning (arxiv.org)

What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking Preservation (arxiv.org)

PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing (arxiv.org)

GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving (arxiv.org)

Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models (arxiv.org)

Guide, Not Bind: Why Defeasible Priors Fail in Augmented Lagrangian Causal Discovery (arxiv.org)

It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories (arxiv.org)

TraveL: Transformer-based Multi-view Path Distributional Representation Learning (arxiv.org)

Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models (arxiv.org)

TIGPO: Temporal Instance-Graph Policy Optimization for Long-Horizon LLM Agents (arxiv.org)

HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews (arxiv.org)

AutoGraphForge: Towards Automated Graph Theory Discovery (arxiv.org)

Beyond "Made with AI": Visualizing Provenance Density to Mitigate the Transparency Penalty (arxiv.org)

Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents (arxiv.org)

DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents (arxiv.org)

Caught in the Story: Narrative Captivity in Multi-turn LLMs Conversation (arxiv.org)

RecurTrace: Adaptive Latent Reasoning with Loop-Time Memory (arxiv.org)