Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does
Research
Research News
New papers, breakthroughs and academic AI research
Language-Conditioned World Modeling for Visual Navigation
Research
Uncertainty-Normalized Margins for Direct Preference Optimization
Research
C-STRIDE: An Observation-Driven AI Digital Twin for Predicting Basin-Wide Flood Fields from Sparse Stream-Gauge Histories
Research
Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
Research
Reserve-Aware Contrast Certificates for Conservative Bandits with Uncertain Baselines
Research
Generalizing the Turing Test to Interactive Agents
Research
RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent
Research
E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models
Research
Distill the Visual Evidence, Not Just the Answer: Cross-World On-Policy Distillation for Vision-Language Models
Research
In-Distribution Imagination for Model-Based Offline Reinforcement Learning
Research
CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models
Research