DramaGrow introduces a regime-aware benchmark and audit protocol for LLM judges evaluating…
A benchmark study evaluates decoder-only LLMs—including Llama, Mistral, Gemma, and Phi 4—o…
CoMixKV addresses the KV-cache memory bottleneck that appears when multiple LLM agents rem…
Researchers introduce R-BiLoGo, a graph-based Transformer surrogate that transfers the res…
fNIRSAtlas consolidates 19 public functional near-infrared spectroscopy datasets into 23 s…
The paper introduces uniform discretization stability, a quantitative refinement of discre…
The paper introduces Selected-Risk Calibration (SRC), a framework that calibrates a learne…
The 2026 Topological Deep Learning Challenge placed graph neural networks and topological …
Agentic· 2026-11-10
Mr.Xu0 views0 discussions
Causal-Discovery-Bench is a verifiable sandbox for evaluating whether LLM agents can auton…
MAGE is a multi-timescale foundation model for electroencephalography. Rather than encodin…
BIBIMBAP evaluates language-driven Building Information Modeling as an executable Text-to-…