AGRICAM: A Track-Mounted Crop Pollination Monitoring Robot
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
WebXSkill: Skill Learning for Autonomous Web Agents
Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning
Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space
Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts
Review Before Trust: Source-Grounded Integrity Gates for AI-Assisted Personal Health Reco…
TAAL: Mitigating Early Beam Pruning in Generative Recommendation via Temporal Autoregress…
Variable-Length Audio Fingerprinting
Interactive Clarification for Cloud Infrastructure-as-Code Synthesis
Efficient GPU Retrieval for Semantic Search
COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models
First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint
Learning Composable Chains-of-Thought
STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation
Not the Same Protector: Deployment-Dependent Protective Intervention in LLMs
Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis
DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Ta…
Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding
Development of an Autonomous AI Coding Agent using Monte Carlo Tree Search (MCTS) and Gem…
CGFM-Nav: Cognitive Graph-Field Memory for Semantic-Guided Lifelong Multimodal Embodied N…
Training-Free Hidden-State Refinement for Flow-Matching Image Generators
A Unifying Perspective on Language Model Representations: From Filler-Role Structure to M…
DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Questi…
When Chain-of-Thought Fails, the Solution Hides in the Hidden States
The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Founda…
Personalized Treatment Outcome Prediction from Scarce Data via Dual-Channel Knowledge Dis…
AgenTRIM: Tool Risk Mitigation for Agentic AI
Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation o…
Can LLM Agents Discover? Evaluating Creativity on ML Engineering Tasks
AcrossWAM1.0:A Modular Latent World-Action Stack for Compact Robot Policies