AI Dataset2026
Provides labeled prompts with full-reference answers (including chain-of-thought and code blocks) and per-example metadata to train edge routing/orchestrator models that decide whether to handle inputs locally or route them to larger models. Includes complexity scores, coding/math flags, routing justifications, and an automated override rule; suited for fine-tuning small models (50M–1.5B) for edge deployment.
Transfers RL-induced policy shifts from a smaller 'weak' teacher to a stronger target by using the teacher's post-/pre-RL log-ratio as a dense implicit reward applied on the student's on-policy states. Enables reuse of RL supervision without running RL rollouts on the target, improving sample/time efficiency.
AI Dataset2026
Structured dataset of internship listings combined with content-performance (SEO) metrics, provided as tabular and textual fields for data-warehouse analysis. Useful for building search/ranking features, training NLP models on internship-related queries, or performing analytics on content performance.
Introduces KronQ, a post-training quantization framework that incorporates gradient covariance via a Kronecker‑factored Hessian to guide input/output weight rotations and sensitivity-driven mixed-precision allocation. Demonstrates stable 2-bit weight-only quantization on LLaMA-3-70B (7.93 PPL).
AI Dataset2026
Provides ~5M model-generated reasoning chains (within 5k sequence length) with structured fields for supervised fine-tuning, reasoning distillation, and instruction tuning. Includes separate fields for prompt, reasoning trace, final answer and a ChatML view; streaming access recommended for large-scale use.
Provides IdeaGene-Bench, a dataset and evaluation suite for scientific-lineage reasoning and lineage-grounded idea generation, representing papers as minimal, typed Idea Genome objects and GenomeDiffs that record inheritance, mutation, loss, import and novel insertion. Includes 1,961 lineage traces, IG-Exam (42 task types) and IG-Arena with a Population-Evolution Score for generation.
Explores unsupervised visual pretraining on visually rich documents to improve language-model intelligence; shows visual-pretrained models outperform text-only counterparts on the same corpora. Key aspects: direct use of images/layouts (no OCR-only pipeline), scalable across backbones and benchmarks.
Proposes Riemannian Isometric Policy Optimization (RIPO) to fix exploration collapse in PPO-style RL for LLMs by aligning policy updates with the policy manifold's Riemannian geometry, improving exploration–exploitation balance and optimization stability across competition benchmarks.
AI Agent2026
Helps produce and revise natural, readable Japanese for work documents by applying a 12-item writing constitution and sudachipy-powered lint to detect and remove “AI-smelling” patterns; includes diagnostic scoring and iterative rewrite loops.
AI Model2026
GGUF-quantized builds of a 1B 'Thinking' MiniCPM5 model fine-tuned on Fable 5 (V2) for local runtimes; enhances tool/function-calling, coding and instruction-following, and supports long contexts (up to 128K tokens).
Builds structured knowledge graphs for retrieval-augmented generation via a multi-step GraphRAG pipeline that separates extraction from consolidation. Key features include typed two-stage extraction, DBSCAN-backed deduplication, LLM summarization, Leiden community detection, and a compact 7B extractor model (Meno-Lite-0.1).
AI Dataset2026
50,000 distilled conversational traces (≈120M tokens) generated from GLM-5.2 for high-reasoning text generation and QA, covering STEM, programming, creative and support dialogues; Apache-2.0 licensed.