Tag

LMSYS-Chat-1M

A public dataset of one million real-world conversations with 25 LLMs, including conversation text, model name, detected language tags, and OpenAI moderation outputs — useful for studying prompt distributions, safety/moderation, and training/evaluating instruction-following models.

ABot World Explorer 500h

Provides 30,969 action-conditioned video episodes, each with source MP4, per-frame keyboard control logs, captions, and a COLMAP sparse pose model — intended for research on action-conditioned video prediction, controllable world models, and representation learning.

IFM/Pretrain-Behaviors

Behavior-focused text corpus for LM pretraining, organized into seven Parquet-backed subsets (reasoning, planning, data-science, games, general, format-rewrites, other). Supports streaming, custom sampling, and large-scale dataset pipelines for research and model training.

Code-Reasoning

Provides multiple Parquet-backed subsets of code problem-solving data (direct answers, chain-of-thought reasoning, and task synthesis) that are streamable and prepared for language-model training and evaluation.

IFM/TxT360-v2

Provides Parquet-backed pretraining subsets of web and synthetic QA text for large-language-model training, including web-high-nltk-qa, web-high-medium, and txt360-qa. Offers streaming access, provenance metadata, and CC BY 4.0 licensing; intended for LM pretraining and research.

IFM/Math-Reasoning

Provides large-scale mathematical problem-solving, rewriting, and dialogue data organized into five Parquet-backed subsets for reasoning-oriented language-model training. Subsets support streaming access, Dataset Viewer inspection, and per-subset provenance metadata; licensed Apache 2.0.

Danbooru 2026 Tag Cleaning Corrections

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.

UltraData-SFT-Agent-2609

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.

Open Yap 1K

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.

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

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.

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

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.

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

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.