AI News

⚡ 9 minutes ago
1
1
A systematic investigation of molecular encoding methods for drug property predictions across neural network and Transformer encoder-based model (arxiv.org)
2
1
Comparative evaluation of training strategies using partially labelled datasets for segmentation of white matter hyperintensities and stroke lesions in FLAIR MRI (arxiv.org)
3
1
Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units (arxiv.org)
4
1
UA-DCM: Uncertainty-aware Causal Decision Making via Effect Bound Decomposition (arxiv.org)
5
1
MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering (arxiv.org)
6
1
Families of Control-Cost-Parametrized Inverse-Optimal Universal Stabilizers (arxiv.org)
7
1
MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation (arxiv.org)
8
1
Alcmean's: Unsupervised community detection using local Laplacian, automatic detection of the number of centers (arxiv.org)
9
1
Nonparametric LLM Evaluation from Preference Data (arxiv.org)
10
1
Cosmo3DFlow: Wavelet Flow Matching for Spatial-to-Spectral Compression in Reconstructing the Early Universe (arxiv.org)
11
1
Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions (arxiv.org)
12
1
Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints (arxiv.org)
13
1
Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence Acceptance (arxiv.org)
14
1
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents (arxiv.org)
15
1
Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning (arxiv.org)
16
1
The Label Horizon Paradox: Rethinking Supervision Targets in Financial Forecasting (arxiv.org)
17
1
On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature (arxiv.org)
18
1
Foundation Inference Models for Ordinary Differential Equations (arxiv.org)
19
1
A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation (arxiv.org)
20
1
An 84-Format Numeric Catalog with Bit-Exact Conformance Vectors: A Vendor-Neutral Reference for FP8, BF16, MXFP4, and Microscaling Formats (arxiv.org)
21
1
Observability for Delegated Execution in Agentic AI Systems (arxiv.org)
22
1
FASE: Fast Adaptive Semantic Entropy for Code Quality (arxiv.org)
23
1
Who Earns the Safety? Intervention-Aware Quantum Predictive Control with Safety Attribution (arxiv.org)
24
1
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger (arxiv.org)
25
1
Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics (arxiv.org)
26
1
Operationalising the Superficial Alignment Hypothesis via Task Complexity (arxiv.org)
27
1
Geometry-Aware Uncertainty Quantification via Conformal Prediction on Manifolds (arxiv.org)
28
1
GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation (arxiv.org)
29
1
Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model (arxiv.org)
30
1
AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing (arxiv.org)
31
1
PTL-Diffusion: Manifold-Aware Diffusion with Periodic Terminal Laws (arxiv.org)
32
1
OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics (arxiv.org)
33
1
A Survey on Large Language Model-Based Game Agents (arxiv.org)
34
1
TQA-Bench: Evaluating LLMs for Multi-Table Question Answering (arxiv.org)
35
1
IDEQ -- Improving Diffusion Models for the Traveling Salesman Problem (TSP) by Leveraging the Structure of the Solution Space (arxiv.org)
36
1
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP (arxiv.org)
37
1
Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations (arxiv.org)
38
1
A Geometric Theory of Cognition for Machine Intelligence (arxiv.org)
39
1
Discovering heuristics in a complex SAT solver with large language models (arxiv.org)
40
1
CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning (arxiv.org)
41
1
MixReasoning: Switching Modes to Think (arxiv.org)
42
1
MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs (arxiv.org)
43
1
TempoBench: Evaluating Temporal Causal Reasoning in Large Language Models (arxiv.org)
44
1
Label-Conditioned Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Curriculum-Gated Contrastive Alignment (arxiv.org)
45
1
A Geometric Unification of Concept Learning with Concept Cones (arxiv.org)
46
1
Understanding Benchmark Language Under Weakened Formal Semantics (arxiv.org)
47
1
Projection and Quantisation: A Unifying View of Learning to Hash, from Random Projections to the RAG Era (arxiv.org)
48
1
Correcting Mean Bias in Text Embeddings: A Refined Renormalization with Training-Free Improvements on MMTEB (arxiv.org)
49
1
SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM (arxiv.org)
50
1
MedVision: Benchmarking Quantitative Medical Image Analysis (arxiv.org)