Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Looped Diffusion Language Models
Language Models Need Sleep
Pixel-Level Pavement Distress Assessment Using Instance Segmentation
Goal-driven Bayesian Optimal Experimental Design for Robust Decision-Making Under Model U…
Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement L…
WhoSaidIt: Human-LLM Collaborative Annotation for Text-Based Multilingual Speaker-Attribu…
Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to …
Look Both Ways Before You Cross: Lifting Cross Fields From 2D Visual Priors
Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
AdvantageFlow: Advantage-Weighted Least Squares for RL in Flow Models
Forgotten Words: Benchmarking NeoBERT for Dementia Detection in Low-Resource Conversation…
The 5 Principles Every AI Research Stack Now Has to Solve
Causal methods for LLM development and evaluation
Deployment-complete benchmarking
Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free …
QUIET: A Multi-Blank Cascaded Story Cloze Benchmark for LLM Creative Generation Capability
EchoPilot: Training-Free Ultrasound Video Segmentation via Scale-Space Semantic Prompting…
LRDDv3: High-Resolution Long-Range Drone Detection Dataset with Range Information and The…
Explore Before You Solve: The Speed--Depth Trade-off in Epistemic Agents for ARC-AGI-3
Predicting Stock Price Direction on Earnings Announcement Days using Multi-modal Deep Lea…
$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing
SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Re…
Merge-Bench: Resolve Merge Conflicts with Large Language Models
DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation
The Timing Dependencies of Trust: Speed, Accuracy, and cBCI Neuro-Decoupling in Human-AI …
SAM3-Assisted Training of Lightweight YOLO Models for Precision Pig Farming
Explaining Too Much? Understanding How Large Language Model Reasoning Traces Influence Pe…
TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning
On the Limits of Model Merging for Multilinguality in Pre-Training