AI News

Revisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal Ensembles (arxiv.org)

Weave Forcing: Compositional Memory Routing for Interactive Long Video Generation (arxiv.org)

Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation (arxiv.org)

Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection (arxiv.org)

Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks (arxiv.org)

When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game (arxiv.org)

LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation (arxiv.org)

SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents (arxiv.org)

Explainable Molecular Structure Inference from GC--MS with Diffusion Models and LLM Reranking (arxiv.org)

MintEval: Do LLMs Implement the Trading Strategy You Asked For? A Behavioural-Equivalence Benchmark for Natural-Language-to-Strategy Code (arxiv.org)

ParaGeo: Decomposing Paralinguistic Variation into a Shared Latent Geometry (arxiv.org)

Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics (arxiv.org)

On-Board Anomaly Detection for Efficient Marine Environmental Monitoring (arxiv.org)

FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution (arxiv.org)

EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras (arxiv.org)

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes (arxiv.org)

Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis (arxiv.org)

TSGuard: A Real-Time Framework for Detecting and Imputing Missing Data in Streaming Time Series (arxiv.org)

Does Physics Live in the Activations? Localizing Physical Quantities in Video Diffusion Models (arxiv.org)

Landscape-Dependent Performance of Photonic Quantum Solvers in QUBO Feature Selection for Financial Risk Detection (arxiv.org)

Hamiltonian locality testing and certification do not achieve the Heisenberg limit (arxiv.org)

Heads, Tails, and AI Fails: LLMs, Randomness, and Human Judgments (arxiv.org)

AstroAgentBench: Evaluating Agentic Planning on Space Mission Planning Tasks (arxiv.org)

LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios (arxiv.org)

NARA: Anchor-Conditioned Representation Learning for Heterogeneous Vector Geoentities (arxiv.org)

Normal-Form Correlation in Markov Games (arxiv.org)

Wrong Organ, Right Physics: Transferring Echocardiography Pretraining to Lung Ultrasound for Tuberculosis Screening (arxiv.org)

SyntaxBench: A Statistical Diagnostic Framework for Character-Level Reasoning in Large Language Models (arxiv.org)

Mixture-of-Experts for Cryptocurrency Order Execution: Training Stability, Tail Risk, and Failure Modes (arxiv.org)

From Patching to Pruning Visual Computation in Vision Language Models (arxiv.org)

Contrastive Neural Embeddings Reveal Individual Traits Beyond Conversational Role (arxiv.org)

Electronic Density versus Geometry for Machine-Learned Molecular Absorption Spectra (arxiv.org)

Generalization of Transformer-Based Neural Quantum States via In-Context Learning (arxiv.org)

XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation (arxiv.org)

Autonomous Robotic Navigation for Endovascular Brain-Computer Interface Access (arxiv.org)

Latent Goal Prediction from Language for Model-Based Planning (arxiv.org)

World Action Planner: Generalizable Robot Decision-Making with Action-Conditioned World Models (arxiv.org)

$T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training (arxiv.org)

Network-in-the-Loop at Scale: GPU-Batched 5G Simulation for Massively Parallel Robot Learning (arxiv.org)

FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs (arxiv.org)

PoCoFL: POlicy-COmpliant Federated Learning (arxiv.org)

From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing (arxiv.org)

Demonstration-Guided Observation Attacks on Black-Box Safe Reinforcement Learning Controllers for Robotic Systems (arxiv.org)

EviDent-CBCT: Evidence-Bottlenecked Report Generation from Dental CBCT under Non-Exhaustive Report Supervision (arxiv.org)

Coco: An Agentic Copilot for the Hardware--Software Co-Design Lifecycle (arxiv.org)

Mitigating Private Data Leakage in LLMs with Whiteout (arxiv.org)

Conditional Capacity and Routing in Mixture-of-Experts Particle Transformers (arxiv.org)

Structural-Functional Brain Connectivity Generation via Multimodal Hypergraph-based Flow Matching (arxiv.org)

Bellman Error Minimization Via Linear Programming Normalization (arxiv.org)

Jumping up and down: Denoiser diffusion models for discrete ordinal data (arxiv.org)