AI Agent2026
Routes natural-language requests to a single “first mate” agent that spawns and supervises multiple autonomous crewmates, each running in an isolated git worktree and producing finished PRs, approved local merges, or standalone investigation reports. Key features include visible session backends, disposable worktrees, explicit project modes, optional persistent secondmates, and an event-driven zero-token watcher.
AI Video Papers2026
Serves interactive, long-lived streaming video-generation sessions by jointly scheduling session placement and GPU autoscaling to meet tight per-chunk latency. Combines migration-aware placement, load-driven autoscaling, coalesced chunk processing, GPU–CPU offloading and NCCL GPU–GPU migration; reports ~37% reductions in worst-case per-chunk latency and GPU operating cost.
AI Dataset2026
Benchmark for evaluating procedural skill evolution in LLM agents: isolates reusable skill bodies, role-specific work surfaces, and hidden oracle assets to measure whether skill refinements transfer across tasks, roles, and model backbones. Includes 382 workplace tasks, 22 skills, and a controlled evaluation protocol.
AI Model2026
Provides a pre-quantized NVFP4 checkpoint of GLM-5.2 for long-context reasoning and coding; reduces model footprint so GLM-5.2 can run on multi‑GPU Blackwell nodes and is ready for inference with SGLang and vLLM.
AI Model2026
NVFP4-quantized variant of Qwen3.6-27B that reduces parameter bits from 16 to 4, cutting disk and GPU memory requirements by ~2.5× while keeping comparable benchmark accuracy; ready for vLLM-based inference on NVIDIA hardware and supports long, multimodal contexts.
AI Model2026
Provides an open-source Mixture-of-Experts coding LLM (397B) optimized for agentic, tool-enabled coding workflows with a 262,144-token context window, OpenAI-compatible API, serving recipes (vLLM/SGLang), and published coding-benchmark results.
AI Model2026
Thinking-off fine-tune for coding-agent workflows that prioritizes fast next-step decisions, lower token usage and stable multi-turn tool calling. Highlights: MoE 35B base, MTP speculative decoding, SWE-bench 62.4% (300 cases). Best for local agent loops and automated debug cycles; requires disciplined harnessing and schema consistency.
Predicts per-request MoE expert footprints from prefill activations and routes decode requests to workers that maximize expert-locality, lowering decode latency by combining offline K-means partitioning with online locality-band routing and a KV-block–coindexed signature cache.
Embodied AI2026
Provides a portable C++ inference runtime to deploy embodied AI models (vision–language–action and world–action) on heterogeneous robot hardware, enabling latency-first batch-1 closed-loop control. Key features include modular multi-rate layers, fused low-latency inference, and extensible head/IO plugins.
AI Agent Papers2026
Proposes SkillOpt-Lite, a minimal pipeline for optimizing LLM agent skills by treating rollout traces as filesystem files and applying trajectory exploration, consensus mining, and independent validation; integrates as a one-line VSCode Copilot command and reports cross-benchmark improvements that let smaller models sometimes outperform larger ones.
AI Model2026
Decides whether a user prompt should be executed locally on an edge small LLM or routed to a larger cloud model, emitting a deterministic pipe-separated decision string. A 51.7M micro-LLM fine-tuned with multi-task sequence generation to predict domain, complexity and code/math flags, optimized for ultra-low latency edge routing.
AI Model2026
Deployment-optimized hybrid MoE LLM (75B total / 9.3B active) produced via Iterative Puzzle compression and Multi-Token Prediction to double server throughput and raise single-GPU concurrency; designed for multilingual reasoning, long-context generation, and high-volume agentic/chat deployments.