What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time? Paper • 2603.19017 • Published 2 days ago • 1
Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA Paper • 2603.08501 • Published 12 days ago
V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising Paper • 2603.16792 • Published 4 days ago • 3
Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control Paper • 2603.09221 • Published 12 days ago
nabla-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space Paper • 2603.04948 • Published 17 days ago • 1
DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks Paper • 2603.01697 • Published 19 days ago • 2
DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks Paper • 2603.01697 • Published 19 days ago • 2
UniT: Unified Multimodal Chain-of-Thought Test-time Scaling Paper • 2602.12279 • Published Feb 12 • 20
UniT: Unified Multimodal Chain-of-Thought Test-time Scaling Paper • 2602.12279 • Published Feb 12 • 20
SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization Paper • 2602.04811 • Published Feb 4 • 2
SWE-Universe: Scale Real-World Verifiable Environments to Millions Paper • 2602.02361 • Published Feb 2 • 60
DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints Paper • 2601.18137 • Published Jan 26 • 35