AI Dataset2026
Provides image-level tag correction instructions for a Danbooru anime-image tagging corpus, listing per-post tags to add or remove. Contains 1.74M normalized correction rows (snapshot 2026-08-30); it's a corrections manifest (no images) intended to be applied to existing metadata.
AI Dataset2026
Provides ~483K agent instruction‑tuning trajectories for supervised fine‑tuning, including tool calls, environment feedback, errors/retries and verification across search, code, office and general agent workflows; static snapshots for SFT and mix‑ratio studies.
AI Dataset2026
Provides 23,625 semi-structured smart-contract audit findings (title, description, PoC, recommendation, normalized severity) for defensive-security research; requires cleaning, deduplication, and PoC filtering before model training.
AI Dataset2026
Provides a dual-channel, channel-separated sample (8.9 hours) and access path to a 1,000‑hour English conversational corpus for commercial and research use. Delivers 48 kHz per-speaker audio, word-level machine transcripts, and per-speaker metadata designed for full‑duplex/turn-taking and ASR/ TTS research.
AI Dataset2026
Provides 10,000 agentic multi-turn coding and reasoning traces from Fable 5.1 with step-by-step chain-of-thought and tool-use, heavily deduplicated and filtered; totals ~500M tokens (1.97 GB). Suited for SFT, distillation, and training long-horizon reasoning and code-generation models.
AI Dataset2026
Turns chemistry and molecular-property questions into verifiable short-answer tasks for language-model training and evaluation, with nearly 50,000 questions drawn from multiple datasets.
AI Dataset2026
Contains 5,000 coding and chain-of-thought reasoning traces generated by Fable 5.1 — ~150M tokens of step-by-step programming CoT. Deduplicated and filtered for high quality; intended for supervised fine-tuning and distillation to improve reasoning in smaller models.
AI Agent Papers2026
Reconstructs executable terminal workspaces from recorded agent trajectories and synthesizes verifiable single- and multi-round coding tasks for agent training; it replays file operations, uses an LLM completion agent to fill missing files/dependencies, and verifies tasks with autogenerated test suites.
Zixuan Fu, Bingxiang He +11Affiliation: University of Chinese Academy of Sciences, Affiliation: Tsinghua University +3
Studies on-policy distillation (OPD) at the data-minimal limit by training on a single query, measuring state coverage and alignment dynamics, and showing OPD is often data-overfed but algorithm-starved.
Builds high-fidelity image generators by pairing a 6B Diffusion Transformer with a frozen LLaDA2.0-Mini vision-language module, relying on extensive image-only pretraining and mid-training; model weights, training code, and recipes are released.
Trains a world-action model that predicts future visual states to guide zero-shot robotic manipulation; introduces CoAE, SVP, IDM and KASO to pretrain generative and action components from scratch on manipulation data, scaling up to 30,000 hours and improving zero-shot success.
AI Dataset2026
Provides layered code pretraining corpora (L2 ~400B tokens, L3 ~150B tokens) across 11 languages by filtering ~192M public GitHub repositories into standardized files, algorithmically relevant selections, and implementation-grounded programming exercises. Includes per-file metadata (role, algo relevance, quality) and serialized task records; released under Apache-2.0.