AI News

⚡ 7 minutes ago
1
1
Echo-POSED: Geometric Self-Distillation for Echocardiography Guidance (arxiv.org)
2
1
Auditable Climate Risk Intelligence from Fragmented ESG Data: Deterministic Orchestration and Imbalance-Aware Learning for Scope 1-3 Validation (arxiv.org)
3
1
Cross-Modal Contrastive Learning of ECG and Angiography Representations for Severe Stenosis Classification (arxiv.org)
4
1
Making Brain-Computer Interfaces More Secure (arxiv.org)
5
1
ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning (arxiv.org)
6
1
Evaluating Transformer and LSTM Frameworks for Prediction in Ungauged Basins (arxiv.org)
7
1
Pruning Deep Neural Networks via the Marchenko--Pastur Distribution (arxiv.org)
8
1
CL-DMDF:Dynamic Multimodal Data Fusion Model Based on Contrastive Learning (arxiv.org)
9
1
Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariate (arxiv.org)
10
1
Aligning Data-Driven Predictors with Allocation: A Decision-Focused Approach to Survival Analysis (arxiv.org)
11
1
Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals (arxiv.org)
12
1
Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systems (arxiv.org)
13
1
Towards Non-Monotonic Entailment in Propositional Defeasible Standpoint Logic (arxiv.org)
14
1
Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition (arxiv.org)
15
1
TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching (arxiv.org)
16
1
Rethinking Neural Width for Alternating Current Optimal Power Flow Proxies (arxiv.org)
17
1
Dynamic Objective Selection with Safeguards and LLM Oversight for Financial Decision-Making (arxiv.org)
18
1
HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models (arxiv.org)
19
1
Multi-Modal Machine Learning for Breast Cancer Recurrence Prediction (arxiv.org)
20
1
LAP: An Agent-to-Instrument Protocol for Autonomous Science (arxiv.org)
21
1
Learning Temporal Causal Structure via Smooth Differentiable Optimization (arxiv.org)
22
1
Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning (arxiv.org)
23
1
EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D PDEs (arxiv.org)
24
1
When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming (arxiv.org)
25
1
Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation (arxiv.org)
26
1
A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs (arxiv.org)
27
1
SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation (arxiv.org)
28
1
The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Constructs (arxiv.org)
29
1
Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent (arxiv.org)
30
1
PrimeSVT: An Automated Memory-aware Pruning Framework with Prioritized Compression Policy for Spiking Vision Transformers (arxiv.org)
31
1
Auditing Engagement Incentives in the Kidfluencer Ecosystem: A Multimodal Weak Supervision Approach (arxiv.org)
32
1
Sample-Size Scaling of the African Languages NLI Evaluation (arxiv.org)
33
1
PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization (arxiv.org)
34
1
NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense (arxiv.org)
35
1
Tonal parsimony in chord-sequence analysis: combining modulation cost and tonal vocabulary (arxiv.org)
36
1
FORGE: Multi-Agent Graduated Exploitation and Detection Engineering (arxiv.org)
37
1
Assessing Region-Level EEG Contributions to Cognitive Workload Prediction (arxiv.org)
38
1
Clustered Self-Assessment: A Simple yet Effective Method for Uncertainty Quantification in Large Language Models (arxiv.org)
39
1
RogueMerge: Robust and Unified Attacks against LLM Model Merging (arxiv.org)
40
1
Lingo_Research_Group at SemEval-2026 Task 9: Evaluating Prompt Variants for Polarization Detection (arxiv.org)
41
1
Explainable Forecasting of Scientific Breakthroughs from Concept Network Dynamics (arxiv.org)
42
1
Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs (arxiv.org)
43
1
BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language (arxiv.org)
44
1
SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts (arxiv.org)
45
1
FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data (arxiv.org)
46
1
Building Reliable Long-Form Generation via Hallucination Rejection Sampling (arxiv.org)
47
1
A Hybrid Approach For Malware Classification Using Secondary Features Fusion (arxiv.org)
48
1
Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation (arxiv.org)
49
1
When to Re-Plan: Subgoal Persistence in Hierarchical Latent Reasoning (arxiv.org)
50
1
GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations (arxiv.org)