AI News

Exploring the Design Space of Reward Backpropagation for Flow Matching (arxiv.org)

DAH-Net: A Dual-Attention Hybrid Network for Interpretable and Robust EEG-Based Emotion Recognition (arxiv.org)

Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors (arxiv.org)

MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning (arxiv.org)

Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs (arxiv.org)

Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective (arxiv.org)

MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance (arxiv.org)

SCOPE: Sequential Causal Optimization of Process Interventions (arxiv.org)

Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes (arxiv.org)

When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models (arxiv.org)

Fact-Augmented Lookahead Planning for LLM Agents (arxiv.org)

A Machine Learning Theory Perspective on Strategic Litigation (arxiv.org)

FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail (arxiv.org)

CITRAS: Covariate-Informed Transformer for Time Series Forecasting (arxiv.org)

Influence Dynamics and Stagewise Data Attribution (arxiv.org)

Integrating Biological-Informed Recurrent Neural Networks for Glucose-Insulin Dynamics Modeling (arxiv.org)

Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs (arxiv.org)

The Whale That Outswam Evolution: Swarm Intelligence Maximises Memory in Connectome Reservoirs (arxiv.org)

Active-Passive Federated Learning for Vertically Partitioned Multi-view Data (arxiv.org)

Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions (arxiv.org)

Uncertainty-Aware Deep Learning for Wildfire Danger Forecasting (arxiv.org)

Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey (arxiv.org)

The Emergence of Reproducibility and Generalizability in Diffusion Models (arxiv.org)

DMT: Demographic Conditioning, Morphology-Enhanced Transformer for Cuffless Blood Pressure Estimation from PPG Signals (arxiv.org)

Multimodal Brain Tumour Classification Using Feature Fusion (arxiv.org)

Do Transformers Actually Help Intrusion Detection? A Temporal Sequence Evaluation on CIC-IDS2017 (arxiv.org)

POPSICLE: Benchmark Datasets for Segmentation and Localization in CryoET (arxiv.org)

ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling (arxiv.org)

What Demonstration Curation Metrics Do to Your Policy (arxiv.org)

Efficient AI-Inspired Reduction of Feynman Integrals via Tube Seeding (arxiv.org)

Do LLMsMakeNeural Distinguishers Wise? (arxiv.org)

An adaptive framework for the axisymmetric pulsar magnetosphere using physics-informed Kolmogorov-Arnold networks (arxiv.org)

ClusBench: The Clustering Benchmark Data Resource You've All Been Waiting For (?) (arxiv.org)

Profy: Interpretable Visualization of Expertise-Dependent Motor Skills Toward Supporting Piano Practice (arxiv.org)

A Bayesian Network Approach for Enhancing Security-Focused Decision Support Systems (arxiv.org)

The Role of Feedback Alignment in Self-Distillation (arxiv.org)

ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models (arxiv.org)

ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity (arxiv.org)

Monte Carlo Pass Search: Using Trajectory Generation for 3D Counterfactual Pass Evaluation in Football (arxiv.org)

Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection (arxiv.org)

Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations (arxiv.org)

Dmsh: A Multi-Agent Reinforcement Learning Framework for All-Quad Mesh Generation (arxiv.org)

Toward Proactive RF Charging Scheduling: Generative AI for Decision Support (arxiv.org)

Accelerating SAV-based optimization via randomized low-rank Hessian approximation (arxiv.org)

Few-step Generative Models as Lossy Compression (arxiv.org)

ASTRA-sim 3.0: Next-Level Distributed Machine Learning Simulations via High-Fidelity GPU and Infrastructure Modeling (arxiv.org)

PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning (arxiv.org)

Magnetic HIP-NN for spin dynamics in disordered itinerant magnets (arxiv.org)

The Order Matters: Sequential Fine-Tuning of LLaMA for Coherent Automated Essay Scoring (arxiv.org)

PatchSTG: Scalable Spatiotemporal Graph Transformers for Traffic Forecasting on Irregular Sensor Networks (arxiv.org)