Research
Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs (opens in a new tab)
arXiv cs.AI ·
Your next cue,
from NOCUE.
Research
TaReD: Tool-Aware Recursive Decomposition for Long-Horizon Tasks (opens in a new tab)
arXiv cs.AI ·
Research
Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning (opens in a new tab)
arXiv cs.AI ·
Research
Open-ended Scientific Discovery with Possibilistic Reasoning (opens in a new tab)
arXiv cs.AI ·
Research
When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization (opens in a new tab)
arXiv cs.AI ·
Research
DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition (opens in a new tab)
arXiv cs.AI ·
Research
Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review (opens in a new tab)
arXiv cs.AI ·
Research
When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction (opens in a new tab)
arXiv cs.AI ·
Research
What to Admit and How to Present: Governing Persistent Memory in LLM Agents (opens in a new tab)
arXiv cs.AI ·