AI News

⚡ 1 minute ago
1
1
Emergence of Context Characteristics Sensitivity in Large Language Models (arxiv.org)
2
1
Disjoint Generation of Synthetic Data (arxiv.org)
3
1
Convergence Bound and Critical Batch Size of Muon Optimizer (arxiv.org)
4
1
Structural Decoupling: A Scaffold-Flow Theory of Generalization and Alignment (arxiv.org)
5
1
The Sample Complexity of Parameter-Free Stochastic Convex Optimization (arxiv.org)
6
1
Formalizing Learning from Language Feedback with Provable Guarantees (arxiv.org)
7
1
Closing the Prior-Posterior Loop: Self-Reflective Molecular Design with Analysis-Driven LLM Iteration (arxiv.org)
8
1
"So There's a Catch-22 Here": How Early Adopters Who Build Multi-Agent LLM Systems Conceptualize Transparency (arxiv.org)
9
1
GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models (arxiv.org)
10
1
The Governance of Human-LLM Interaction: Safety Gating, Civility Steering, and Affective Default Lock-In (arxiv.org)
11
1
Closing the Sim-to-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDR (arxiv.org)
12
1
RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT (arxiv.org)
13
1
LCAM: A Framework for Diagnosing Interactional Alignment Failures in Con-versational AI (arxiv.org)
14
1
Human-Centered Benchmarking of Driver Monitoring Models (arxiv.org)
15
1
Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Data (arxiv.org)
16
1
Continual Quadruped Robots Coordination via Semantic Skill Discovery (arxiv.org)
17
1
Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method (arxiv.org)
18
1
Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions (arxiv.org)
19
1
"I understand your perspective": LLM Persuasion and Sycophancy through the Lens of Communicative Action Theory (arxiv.org)
20
1
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? (arxiv.org)
21
1
Enhancing Strawberry Yield Forecasting with Backcasted IoT Sensor Data and Machine Learning (arxiv.org)
22
1
LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty (arxiv.org)
23
1
phepy: Visual benchmarks and improvements for out-of-distribution detectors (arxiv.org)
24
1
AccioScene: Compositional 3D Scene Generation via Graph Diffusion and Interaction-driven Critics (arxiv.org)
25
1
Advancements in Machine Learning and Deep Learning for Early Detection and Management of Mental Health Disorder (arxiv.org)
26
1
ePC: Fast and Deep Predictive Coding in Digital Simulation (arxiv.org)
27
1
Graph-to-SFILES: Control structure prediction from process topologies using generative artificial intelligence (arxiv.org)
28
1
BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching (arxiv.org)
29
1
Zero and Few Shot Load Forecasting with Large Language Models (arxiv.org)
30
1
Modeling Stochastic Conditional Dynamics from Sparse Observations via Kernel-Stabilized Flow Matching (arxiv.org)
31
1
EgoAERO: Learning Dexterous Manipulation from a Single Egocentric Video without Object Assets (arxiv.org)
32
1
What's the Point? Spatial Grammar & Index Resolution for Sign Language Processing (arxiv.org)
33
1
GIScholarBench: Benchmarking LLM Overconfidence in GIS Research (arxiv.org)
34
1
Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems (arxiv.org)
35
1
Voting Protocols as Coordination Mechanisms for Role-Constrained Multi-Agent Tutoring Systems (arxiv.org)
36
1
Discovering Data Structures: Nearest Neighbor Search and Beyond (arxiv.org)
37
1
Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Design (arxiv.org)
38
1
Federated Large Language Models: Current Progress and Future Directions (arxiv.org)
39
1
Mean Teacher based SSL Framework for Indoor Localization Using Wi-Fi RSSI Fingerprinting (arxiv.org)
40
1
Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape (arxiv.org)
41
1
Repair Before Veto, When Repair Is Hidden: Quantum-Accessible Features for Repair-Augmented Constraint Learning (arxiv.org)
42
1
IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment (arxiv.org)
43
1
GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence (arxiv.org)
44
1
Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation (arxiv.org)
45
1
Summarization is Not Dead Yet (arxiv.org)
46
1
CATPO: Critique-Augmented Tree Policy Optimization (arxiv.org)
47
1
Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook (arxiv.org)
48
1
Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems (arxiv.org)
49
1
Improving Multimodal Reasoning via Worst Dimension Optimization (arxiv.org)
50
1
Reconstructing and forecasting disease trajectories of patients with Alzheimer's disease using routine data in resource-constrained settings (arxiv.org)