First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
ScenePilot: Grow-and-Repair Policy for Text-Driven 3D Indoor Scene Generation
CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration
Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents
Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis
GUI-PRA: Process Reward Agent for GUI Tasks
MobileDreamer: Generative Sketch World Model for GUI Agent
Beyond Token-Level Guidance: Inference-Time Alignment of Specialized LLMs via Cross-Famil…
Language-Guided Tuning: Configuration Optimization for Automated ML Research
Not Your Typical Sycophant: The Elusive Nature of Sycophancy in Large Language Models
One AI Signal, Many Human Judgments: A Bayesian Cascade Analysis of AI-based Credibility …
From Location Phrases to Geographic Entities: Task-Adapted Retrieval for People Search
Useful Memories Become Faulty When Continuously Updated by LLMs
Using Prosody to Predict Syntactic Structure
Stride-k Subsampling: Train-Free Audio Token Reduction for Whisper
Explainable Artificial Intelligence (XAI) in Computational Pathology: Definitions, Taxono…
Dec-BFTRL: Squre-Root Regret for Decentralized Online Upper-Linearizable Optimization und…
Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data
Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs
Evaluating the Hidden Costs of Personalization in Large Language Models
MineCEraft: Evaluating Language Models as Construction Engineers in the World of Minecraft
ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assist…
A Composition-Aware Pretraining Framework for Geospatial Foundation Models
A Mental Model Based Framework of Trust
Agentic AI uncovers conserved cross-tissue protein co-abundance programs inaccessible to …
Capability-Stratified Degradation in Ternary Language Models
COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models
Personas Differ from Native-Language Generation: Language Pathways Shape LLM Interpersona…
BCPPO: Bachelier-Inspired Constrained Proximal Policy Optimization for Tail-Risk-Aware Sa…
Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autono…