Research across all areas of computer science, from theoretical foundations to applied systems.
A shared feed-forward memory and iterative attention reasoners retain comparable downstream scores while reducing continual-pretrained 35B-model inference time by nearly 4×.
An ontology, evaluation scheme, and 600,000-skill repository let agents retrieve and compose prior procedures, reporting 40% higher rewards with 30% fewer steps.
A shared policy contract and isolated client/server runtime let 42 robot policies connect to simulations and real-robot evaluation without pairwise adapters.
An intent engine and agentic meta-control layer steer existing recommendation stages, lifting GMV 1.31% when extended through fine ranking.
Kimi K2.5 couples joint text-vision training with dynamically scheduled parallel subagents, improving agentic search scores while reducing time to target quality.
A 2.8T-parameter MoE combines Delta Attention, 16-of-896 expert routing, and agentic reinforcement learning to approach leading proprietary systems at lower task cost.
A 397B-A17B mixture-of-experts agent learns screenshot-only keyboard and mouse control from verifiable interactive trajectories, improving OSWorld-Verified performance to 86.2.
An 8B vision-language model predicts image-space waypoints from a single RGB stream, reaching 77.4% unseen-environment success while cutting supervised training tokens 22×.
A director-designed taxonomy and evaluation agent track human model rankings at Spearman ρ=0.95–0.96 while exposing multi-shot and dynamic-aesthetics failures.
ROCS separates request-side and candidate-side computation, reaching up to 3× higher retrieval QPS and 50% higher ranking QPS in production.
