AI News

⚡ 10 minutes ago
1
1
Cost-Aware Routing for Efficient Text-To-Image Generation (arxiv.org)
2
1
Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency (arxiv.org)
3
1
Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games (arxiv.org)
4
1
Belief-Space Control for Personalized Cancer Treatment via Active Inference (arxiv.org)
5
1
AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning (arxiv.org)
6
1
PRISM: Parallel Residual Iterative Sequence Model (arxiv.org)
7
1
A Comprehensive Inference-Time Augmentation Framework in Physiological Signals: Application to PPG-Based AF Detection (arxiv.org)
8
1
Validation-Stage Combinatorial Fusion Analysis for Imbalanced Credit-Card Fraud Detection (arxiv.org)
9
1
When Metrics Disagree: A Meta-Analysis of Knowledge-Graph-Completion Model Benchmarking (arxiv.org)
10
1
Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing (arxiv.org)
11
1
MinhwaNet: Faithful but Insufficient Object Grounding in Korean Folk Painting (arxiv.org)
12
1
Gradient-Guided Reward Optimization for Inference-time Alignment (arxiv.org)
13
1
Sampling Triangulations and Calabi-Yau Threefolds with Autoregressive GNNs (arxiv.org)
14
1
Spiking Neural Network inference on FPGAs with hls4ml (arxiv.org)
15
1
When to Align, When to Predict: A Phase Diagram for Multimodal Learning (arxiv.org)
16
1
Predicting Future Behaviors in Reasoning Models Enables Better Steering (arxiv.org)
17
1
Algorithmic and Minimax Complexities in Kernel Bandits (arxiv.org)
18
1
COGENT: Continuous Graph Emulators with Neural Ordinary Differential Equations for Long-Term Physical Forecasting (arxiv.org)
19
1
First-Order Trajectory Matching: Fast Ensemble Predictions of Chaotic, Turbulent, Stochastic Systems (arxiv.org)
20
1
Robust Regression of General ReLUs with Queries (arxiv.org)
21
1
Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept-Grounded Orthogonal Inference (arxiv.org)
22
1
RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty (arxiv.org)
23
1
ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents (arxiv.org)
24
1
Adoption of Generative Artificial Intelligence in the German Software Engineering Industry: An Empirical Study (arxiv.org)
25
1
torch-sla: Differentiable Sparse Linear Algebra with Adjoint Solvers and Sparse Tensor Parallelism for PyTorch (arxiv.org)
26
1
V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions (arxiv.org)
27
1
Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making (arxiv.org)
28
1
On the Condition Number Dependency in Bilevel Optimization (arxiv.org)
29
1
TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning (arxiv.org)
30
1
Whisfusion: Parallel ASR Decoding with Masked Diffusion (arxiv.org)
31
1
How can we assess human-agent interactions? Case studies in software agent design (arxiv.org)
32
1
ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering (arxiv.org)
33
1
Overcoming Rank Collapse in Feedback Alignment (arxiv.org)
34
1
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning (arxiv.org)
35
1
Efficiently Learning Drifting Halfspaces with Massart Noise (arxiv.org)
36
1
Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning (arxiv.org)
37
1
Unifying Local Communications and Local Updates for LLM Pretraining (arxiv.org)
38
1
Exploring the Design Space of Reward Backpropagation for Flow Matching (arxiv.org)
39
1
DAH-Net: A Dual-Attention Hybrid Network for Interpretable and Robust EEG-Based Emotion Recognition (arxiv.org)
40
1
Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors (arxiv.org)
41
1
MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning (arxiv.org)
42
1
Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs (arxiv.org)
43
1
Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective (arxiv.org)
44
1
MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance (arxiv.org)
45
1
SCOPE: Sequential Causal Optimization of Process Interventions (arxiv.org)
46
1
Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes (arxiv.org)
47
1
When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models (arxiv.org)
48
1
Fact-Augmented Lookahead Planning for LLM Agents (arxiv.org)
49
1
A Machine Learning Theory Perspective on Strategic Litigation (arxiv.org)
50
1
FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail (arxiv.org)