Mind Your Tone: Does Tone Alter LLM Performance?
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Quantum-Enhanced Adversarial Robustness in Artificial Intelligence
Context Distillation as Latent Memory Management
TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation M…
Bridging the Sim-to-Real Gap in Reinforcement Learning-Based Industrial Dispatching throu…
Balancing Multimodal Learning through Label Space Reshaping
Emergent Semantic Representations in World Models through Physical Interaction without Li…
Self-Play Reinforcement Learning under Imperfect Information in Big 2
GPF-LiveNews: A Streaming Evaluation Protocol for Group-Conditioned Framing in Large Lang…
Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
Wait! There's a Way Out: A Decision Mechanism for Forecasting Conversational Derailment
OrcaRouter: A Production-Oriented LLM Router with Hybrid Offline-Online Learning
CSULoRA: Closest Safe Update Low-Rank Adaptation
LLMs believe false statements even after explicit warnings that they're false
The Billion-Dollar Quest to Build AI That Improves Itself
Various LLM Smells
Archon: A Unified Multimodal Model for Holistic Digital Human Generation
Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geom…
IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generat…
AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection
The Model Isn't the Agent Anymore
CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference …
No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
xModel-KD: Cross-modal Knowledge Distillation for 3D Scene Perception using LiDAR
Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence
DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evalua…
Native Audio-Visual Alignment for Generation
RAISE: RAG Design as an Architecture Search Problem
Test Time Training for Supervised Causal Learning
RSI is the new AGI — and it’s just as hard to pin down