MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
Embedded Machine Learning for Microcontroller-Class Edge Devices: Data, Feature, Evaluati…
Descriptor: Certus Caliber Classification Gunshot Dataset (C3GD)
Model Validation of Agentic AI Systems: A POMDP-Based Framework for Belief-State, Forecas…
Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Visi…
ReAge3D: Re-Aging 3D Faces with View Consistency
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons i…
Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents
NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Hor…
A Red-Team Study of Anthropic Fable 5 & Opus 4.8 Models
Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search
SoK: AI-Augmented Binary Reversing
FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness
Distributed General-Purpose Agent Networks: Architecture, Key Mechanisms, and Prototypes
Treatment Response Optimized Clinical Decision Support AI System via Digital Twin Simulat…
The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
China Watchdog Urges More IPOs From AI, Hong Kong Listed Firms
Gender Bias in LLM Hiring Decisions: Evidence from a Japanese Context and Evaluation of M…
PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes
PragReST: Self-Reinforcing Counterfactual Reasoning for Pragmatic Language Understanding
Towards Anomaly Detection on Relational Data
BCL: Bayesian In-Context Learning Framework for Information Extraction
General Atlantic in Talks to Lead Funding for China’s Kling AI
Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Re…
HSBC Expects Over $100 Million Gains From Using Google AI Tools
Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Counting
Hierarchical Multi-Modal Retrieval for Knowledge-Grounded News Image Captioning
GLM-5.2 🤖, DeepSeek raises $7.4B 💰, Android MCP 📱
Introducing LifeSciBench