Evaluating the Efficacy of LLMs to Emulate Realistic Human Personalities
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
LLM4LLM: Bridging Kernel Benchmarks and Real Deployment via Closed-Loop Agentic Optimizat…
MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks
From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-T…
An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
Sycophants in the Courtroom: Are LLMs Fragile to Juridical Authority and Evolving Legal S…
LiteEvent-AE: Lightweight Autoencoder for Event-Based Vision on Low-Latency Energy-Constr…
Relative Time Intervals Representation for Word-level Timestamping with Masked Training
SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document U…
QML for Quantum Sensing under Measurement-Induced Information Loss
Evolutionary Recurrent Decision Model in Developing Adaptive and Maladaptive Behaviors
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generati…
AI is hitting entry-level jobs hardest, Stanford study finds
MetaRoCE: A New RDMA Transport Built for AI-Scale Ethernet
ReWorld: An Interactive World Model with Long-Horizon Memory
FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors
When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliatio…
SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Re…
Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models
What's the Catch? Evaluating Temporal Consistency in Vision-Language Models
RAD: Rule-Augmented Relational Anomaly Detection
ProxyFormer: A Dual-Stream Proxy Architecture for Ultra-Long Context and High-Resolution …
SkillAlchemy: Open-World Agent Skill Creation
Adaptive Item-based Collaborative Structures via Noise Rescheduling in Diffusion for Gene…
Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data
Modalities Should Talk to Each Other: Dual-Stream Multimodal Learning for Long-Horizon In…
FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming…
Test-Time Adaptation for ECG Classification via SQI-Gated Self-Training and Beat-Rhythm C…
Controllable blind deblurring with diffusion models