AI News

⚡ 2 minutes ago
1
1
Multi-Level Analyzation of Imbalance to Resolve Non-IID-Ness in Federated Learning (arxiv.org)
2
1
When Design Rules Break: Benchmark Composition Determines Whether Label Informativeness Predicts GNN Aggregator Choice (arxiv.org)
3
1
DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction (arxiv.org)
4
1
Deep Slice Interpolation for Reducing Through-Plane Anisotropy and Noise in Head CT (arxiv.org)
5
1
Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training (arxiv.org)
6
1
GAGI: A Gini-Adjusted GDP-per-Capita Index for Distribution-Aware Macroeconomic Welfare Monitoring (arxiv.org)
7
1
Anomaly Detection and Root Cause Analysis for Microservice Systems (arxiv.org)
8
1
Interactions Between Crosscoder Features: A Compact Proofs Perspective (arxiv.org)
9
1
Conformal Prediction for Neural Operators: Distribution-Free Uncertainty Quantification in Physics Simulation (arxiv.org)
10
1
Co-GLANCE: Uncertainty-Aware Active Perception for Heterogeneous Robot Teaming (arxiv.org)
11
1
SPDM: Geometry-Modulated State Space Modeling with Manifold Constraints for Time Series Forecasting (arxiv.org)
12
1
IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference (arxiv.org)
13
1
RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference (arxiv.org)
14
1
The Whale That Outswam Evolution: Swarm Intelligence Maximises Memory in Connectome Reservoirs (arxiv.org)
15
1
Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History (arxiv.org)
16
1
When Attribution Patching Lies: Diagnosis and a Second-Order Correction (arxiv.org)
17
1
HMAF: A Hierarchical Multi-Slot GD-RTB Allocation Framework (arxiv.org)
18
1
Tractogram foundation model (arxiv.org)
19
1
TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts (arxiv.org)
20
1
QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning (arxiv.org)
21
1
SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs (arxiv.org)
22
1
Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning (arxiv.org)
23
1
LLM-as-a-Discriminator: When Synthetic Tables Still Look Real (arxiv.org)
24
1
Representation Curriculum: Stagewise Training for Robust Ranking and Allocation (arxiv.org)
25
1
PreAct-Bench: Benchmarking Predictive Monitoring in LLMs (arxiv.org)
26
1
SocraticPO: Policy Optimization via Interactive Guidance (arxiv.org)
27
1
SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs (arxiv.org)
28
1
Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation (arxiv.org)
29
1
From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents (arxiv.org)
30
1
Blurry Window Attention (arxiv.org)
31
1
Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models (arxiv.org)
32
1
Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting with Distribution-Free Coverages (arxiv.org)
33
1
Hyperbolic Neural Population Geometry Benefits Computation (arxiv.org)
34
1
CANVAS: Captioning Art with Narrative Visual-Audio AI Systems (arxiv.org)
35
1
The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans (arxiv.org)
36
1
An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models (arxiv.org)
37
1
Integrated Real-Time Motion Tracking and AI Analysis for Athletic Performance Optimization (arxiv.org)
38
1
Pushing the limits of one-dimensional NMR spectroscopy for automated structure elucidation using artificial intelligence (arxiv.org)
39
1
Accounting for AI Inference in Corporate GHG Inventories: A Four-Tier Methodology for Scope 3 Category 1 Reporting (arxiv.org)
40
1
Post-Quantum Secure Federated DeFi for Inclusive Banking (arxiv.org)
41
1
Dynamic Linear Attention (arxiv.org)
42
1
STORM: Stepwise Token Optimization with Reward-Guided Beam Search (arxiv.org)
43
1
Cost-Aware Routing for Efficient Text-To-Image Generation (arxiv.org)
44
1
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment (arxiv.org)
45
1
Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency (arxiv.org)
46
1
Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games (arxiv.org)
47
1
Belief-Space Control for Personalized Cancer Treatment via Active Inference (arxiv.org)
48
1
AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning (arxiv.org)
49
1
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics (arxiv.org)
50
1
PRISM: Parallel Residual Iterative Sequence Model (arxiv.org)