Latest AI research — helucino

13m
[AINews] Jeff, Sanjay, Oriol, and Quoc depart DeepMind; Demis to Chair; Koray to SVP — what is going on at GDM???
Latent Space
47m
A Long-Run Persistence Theory for AI Systems under the Redundancy-Adjusted Artificial Age Score (AAS)
arXiv cs.AI
47m
Item Response Theory for AI Safety
arXiv cs.AI
47m
DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Features
arXiv cs.AI
47m
Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models
arXiv cs.AI
47m
AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering
arXiv cs.AI
47m
Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains
arXiv cs.AI
47m
Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness
arXiv cs.AI
47m
Toward Integrating Adaptive Experience Replay and Online Uncertainty Estimation in Safe Actor-Critic Optimal Control
arXiv cs.AI
47m
Agreement Before Diversity: Verification-First Complementarity for Heterogeneous Language-Model Coordination
arXiv cs.AI
47m
A Model Merging Approach for Continual MLLM Unlearning
arXiv cs.AI
47m
Wiring Beats Blending: What Transfers Between Transformer Sizes -- and What Doesn't
arXiv cs.AI
47m
MERaLiON-GR: Speech Gender Recognition Model for English and SEA Languages
arXiv cs.AI
47m
Calibrating Artificial Guilt: Neurally Grounded Reward Shaping for Prosocial Multi-Agent Reinforcement Learning
arXiv cs.AI
47m
On Hamming-Lipschitz Type Stability of the Subdominant (Minmax) Ultrametric: Theory and Simple Proofs
arXiv cs.AI
47m
Representational separation between unitary and channel quantum generative models via shared classical randomness at shallow depth
arXiv cs.AI
47m
Not Every Divergence Should Be Suppressed: Counterfactual Recoverability in On-Policy Distillation
arXiv cs.AI
47m
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
arXiv cs.AI
47m
Provable Limits and Certified Deferral for Verbalized Uncertainty in Small Language Models
arXiv cs.AI
47m
Strategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical Systems
arXiv cs.AI
47m
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
arXiv cs.AI
47m
Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent
arXiv cs.AI
47m
Interpretable Fuzzy Inference for UAV Target Tracking Using Bounding-Box Geometry
arXiv cs.AI
47m
Zero-shot reasoning for simulating scholarly peer-review
arXiv cs.AI
47m
Image Classification Using CNN-QNN Hybrid Model with Optimized Correlated Features
arXiv cs.AI
47m
Online Goal Recognition using Path Signature and Dynamic Time Warping
arXiv cs.AI
47m
CogniFold: Always-On Proactive Memory via Cognitive Folding
arXiv cs.AI
47m
Towards a satellite image manipulation and deepfake localization benchmark dataset
arXiv cs.AI
47m
Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models
arXiv cs.AI
47m
Monte Carlo Tree Search for Table-to-Multimodal Report Generation
arXiv cs.AI
47m
A Trust-region Framework for Moment Estimation
arXiv cs.AI
47m
MarsCast: Transfer Learning of AI Weather Foundation Models to Planetary Atmospheres
arXiv cs.AI
47m
The Effect of Perceived Race and Gender on Police Language Use: Experimental Evidence from VR Simulations
arXiv cs.AI
47m
NuclearDiffusion: Text-to-Image Foundation Models for Learning Nuclear Energy Concepts
arXiv cs.AI
47m
Towards Trustworthy Hypergraph Neural Networks under Label Noise
arXiv cs.AI
47m
SimMOF: AI agent for Automated MOF Simulations
arXiv cs.AI
47m
Compass: Continuously Aligning Social Media Feeds via In-Situ Reflections
arXiv cs.AI
47m
GUARD: Grounding Uncertainty and Ablation-Based Risk Detection for Diffusion-Based VLAs
arXiv cs.AI
47m
COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation
arXiv cs.AI
47m
ORACLE: A Multi-Objective Reinforcement Learning-Based Analog Circuit Design Optimizer with Large Language Models-Guided Exploration
arXiv cs.AI
47m
MESH: Memory-Efficient Sinkhorn Optimization for Mixture-of-Experts Training
arXiv cs.AI
47m
Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Mediated Reasoning
arXiv cs.AI
47m
Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO
arXiv cs.AI
47m
Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation
arXiv cs.AI
47m
Out-Of-The-Loop Multi-Fidelity Bayesian Optimization
arXiv cs.AI
47m
AFD-Ledger: Deployment Provisioning for Attention--FFN Disaggregation
arXiv cs.AI
47m
Interoceptive Attention as Dynamic Homeostatic Prioritization in a Foraging Agent
arXiv cs.AI
47m
EviGraph: Evidence-Guided Autonomous Research Agents
arXiv cs.AI
47m
C$^2$MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning
arXiv cs.AI
47m
Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs
arXiv cs.AI
47m
Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language
arXiv cs.AI
47m
Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
arXiv cs.AI
47m
When Absence Is Evidence: Evaluating Completeness-Sensitive Negative Reasoning in Large Language Models
arXiv cs.AI
47m
Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks
arXiv cs.AI
47m
Joint UAV Flight and Opportunistic Routing under Reinforcement Learning for Delay-Tolerant Networks
arXiv cs.AI
47m
RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
arXiv cs.AI
47m
EA-Graph: Artifact-Anchored Verification Memory for Coding Agents under Upstream Drift
arXiv cs.AI
47m
Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
arXiv cs.AI
47m
Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders
arXiv cs.AI
47m
Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipation
arXiv cs.AI