AI News

⚡ 12 minutes ago
1
1
Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics (arxiv.org)
2
1
When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming (arxiv.org)
3
1
Trans GAN-WT: A Feature Extraction and Interactive Learning-Based Anomaly Detection Model for Wind Turbine Time Series Data (arxiv.org)
4
1
A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs (arxiv.org)
5
1
Strongly Polynomial Time Complexity of Policy Iteration for $L_\infty$ Robust MDPs (arxiv.org)
6
1
Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery (arxiv.org)
7
1
Calibrating Urban Traffic Simulation from Sparse Road Observations via Genetic Optimization (arxiv.org)
8
1
BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents (arxiv.org)
9
1
Re-Evaluating Continual Learning with Few-Shot Adaptation (arxiv.org)
10
1
EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management (arxiv.org)
11
1
Leveraging BART to Assess CS1 C++ Programming Assignments using Rubric-based Criteria (arxiv.org)
12
1
P\textsuperscript{2}-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization (arxiv.org)
13
1
Resource-Constrained Adaptive Inference for Sequential Pricing (arxiv.org)
14
1
SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling (arxiv.org)
15
1
Self-Soupervision: Cooking Model Soups without Labels (arxiv.org)
16
1
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis (arxiv.org)
17
1
PURGE: Projected Unlearning via Retain-Guided Erasure (arxiv.org)
18
1
From Control Boundary to Insurance Claim: Reconstructing AI-Mediated Losses Through the CER Framework (arxiv.org)
19
1
Pretraining Language Models on Historical Text (arxiv.org)
20
1
When to Re-Plan: Subgoal Persistence in Hierarchical Latent Reasoning (arxiv.org)
21
1
Dynamic Short Convolutions Improve Transformers (arxiv.org)
22
1
Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching (arxiv.org)
23
1
LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems (arxiv.org)
24
1
FederatedSkill: Federated Learning for Agentic Skill Evolution (arxiv.org)
25
1
DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data (arxiv.org)
26
1
Bayesian Tensor Decomposition with Diffusion Model Prior (arxiv.org)
27
1
Multi-Modal Machine Learning for Breast Cancer Recurrence Prediction (arxiv.org)
28
1
Learning Temporal Causal Structure via Smooth Differentiable Optimization (arxiv.org)
29
1
Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It) (arxiv.org)
30
1
The DeepSpeak-Agentic Dataset (arxiv.org)
31
1
Hand Trajectory Fusion for Egocentric Natural Language Query Grounding (arxiv.org)
32
1
Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation (arxiv.org)
33
1
Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models (arxiv.org)
34
1
Dynamic Objective Selection with Safeguards and LLM Oversight for Financial Decision-Making (arxiv.org)
35
1
EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents (arxiv.org)
36
1
A Cartesian-3j Framework for Machine Learning Interatomic Potentials (arxiv.org)
37
1
Towards Blind Lens Aberration Correction via Large LensLib Pre-training and Discrete Degradation Priors (arxiv.org)
38
1
Learning to See via Epiretinal Implant Stimulation in silico with Model-Based Deep Reinforcement Learning (arxiv.org)
39
1
Rethinking Neural Width for Alternating Current Optimal Power Flow Proxies (arxiv.org)
40
1
FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data (arxiv.org)
41
1
ScoreStop: Gradient-based early stopping using functional score tests (arxiv.org)
42
1
State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation (arxiv.org)
43
1
FORGE: Multi-Agent Graduated Exploitation and Detection Engineering (arxiv.org)
44
1
AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking (arxiv.org)
45
1
GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond (arxiv.org)
46
1
PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion (arxiv.org)
47
1
Low-Frequency Shortcuts in Texture-Driven Visual Learning (arxiv.org)
48
1
q0: Primitives for Hyper-Epoch Pretraining (arxiv.org)
49
1
dstack-capsule: Pod-Level Remote Attestation for Confidential Workloads on Kubernetes (arxiv.org)
50
1
Constitutional On-Policy Safe Distillation (arxiv.org)