AI Agent Papers2026
Turns raw datasets into verifiable multimodal news features via a multi-agent newsroom pipeline. Key innovations: (1) an Inspector that links each claim to data/code/external references for re-execution and audit; (2) multimodal asset generation (interactive maps, audio, visuals) tailored to the story.
AI Coding2026
Provides a locally runnable, quantized GGUF release of Gemma 4 12B fine-tuned for Python coding with chain-of-thought distilled from Composer 2.5 and supplemented by Fable 5. Multiple quant options for low‑VRAM setups and execution‑verified training traces. Not safety‑aligned; validate before production.
AI Dataset2026
Contains a sanitized Claude Code (Fable 5) JSONL transcript of a session that procedurally built a Boeing 747 in Three.js, including assistant messages, tool calls, and base64 screenshots — useful for studying agent trace, tool use, and vision self‑verification workflows.
AI Model2026
Provides GGUF quantized weights and runnable instructions to run CohereLabs' North-Mini-Code-1.0 (30B A3B MoE) locally via llama.cpp or vLLM; includes quant files, build/run notes, and recommended sampling and tool-use settings for agentic coding.
AI Agent Papers2026
Synthesizes shortcut-resistant search tasks to train deep search agents by controlling four shortcut risks across entity selection, evidence-graph construction, question formulation, and adversarial refinement. Produces training trajectories with longer pre-answer search and fewer shortcut patterns; code will be released on GitHub.
AI Dataset2026
Collects raw coding-agent sessions—developer prompts, model replies, tool calls, and command output—donated from public repositories and anonymized locally. Organized by agent harness (raw session files + Parquet table), useful for studying agent behavior and tool use; anonymization is best-effort.
AI Model2026
An agentic multimodal coding model for long-horizon software tasks: MoE architecture (1T params, 32B activated), 256K context, image/video input, native int4 quantization and preserved chain-of-thought (thinking) mode. Tuned for multi-step coding workflows and vLLM/SGLang deployment.
AI Model2026
A 3B-parameter causal LLM tuned for verifiable multi-step reasoning in math, coding and STEM using a Spectrum-to-Signal post-training pipeline (SFT, RL, offline self-distillation); not recommended for tool-calling/agent tasks.
AI Dataset2026
A JSON dataset of ~1.1M anonymized coding-assistant instruction→response interactions for training and evaluating code-generation and instruction-following models; packaged for use with pandas/polars and sized at ~459 MB.
AI Agent Papers2026
Moves repository search into a dedicated exploration subagent that issues parallel read-only READ/GLOB/GREP calls and returns compact file:line citations. Trained (4B–30B) with SFT+RL, it reduces main-agent token use up to ~60% and raises end-to-end success by up to ~5.5%.
AI Dataset2026
Curates ~1.1M instruction–response examples for 'vibe coding' scenarios where developers prompt LLMs to produce implementation plans, architecture choices, and deployment steps. Covers conversation memory, prompt templates, model routing, streaming responses, and scaling considerations; Apache-2.0.
Learns, maintains, and runs unified world models for Physical AI using a cross-embodiment pretraining curriculum and a hybrid linear temporal-attention architecture. Emphasizes long-horizon state persistence, theoretical bounds on error accumulation, and deployment-aware low-latency inference for real-world embodied agents.