AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Cont…
From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness fo…
Short-term load forecasting under EU-AI Act Requirements in Safety-Critical Environments:…
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models
When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
ContextWeave: A Real-World Workflow Benchmark
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Plurali…
SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution
A Multi-Layer System for Ultra-High-Resolution Static 360-Degree Telepresence
Equation-Free Period-Aware Forecast-Error Contraction for Estimating Negative Largest Lya…
Different Perturbations, Different Mechanisms: Understanding Continued Pre-training for Z…
APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with A…
Effective pruning of task-trained recurrent neural networks using noisy fluctuations and …
From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking
Computationally Efficient Collaborative Communication Via Regularity-Based Coarsening
Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence (2025)
CoCo-IR: Contextual Composed Image Retrieval
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reason…
DASyR-LLM: Domain-Aware Symbolic Regression with LLMs for Kinetic Model Discovery
Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation
VQ-VAD: Vector-quantized Motion Representation Learning for Human-centric Video Anomaly D…