Discover the Best AI Resources

OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs

Benchmarks assistant-style, multi-turn interaction for omni-modal LLMs on real-time video by reverse-engineering Internet clips into guided multi-turn interactions. It provides predefined priors and segment-level constraints so models must follow exact routes while being evaluated on answer correctness, timing, visual-prompt handling, and context retention.

Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

Proposes “Graph Engineering”: using explicit, dynamic graphs to represent tasks, agents, tools, and system state so LLM-based agent systems can coordinate, persist, and evolve. Surveys principles, methods, applications, and curates related resources.

Türk İçtihat Korpusu (Turkish Court Decisions)

Provides a CC0-licensed corpus of 11,045,085 Turkish court decisions (1962–2026) in Parquet: 31.5 billion characters, 5.5 GB—designed for retrieval, summarization, classification and RAG workflows.

Spark-X2.5-4B

A 4B-parameter on-device general-purpose LLM for chat, writing, translation, coding and agentic workflows with native 1,000,000-token context. Uses a hybrid attention design to enable long-context efficiency, pretrained on ~20T tokens, and compatible with vLLM, llama.cpp, Ollama and LM Studio.

Pipecat PhoneLLM Alpha 1

Open-weights LLM fine-tuned for phone-based voice agents that prioritizes low latency and reliable tool/function calling. Based on NVIDIA Nemotron 3 Nano (30B total, 3.5B active), supports very long contexts (262,144 tokens) and recommends temperature=0 with thinking disabled for deployment.

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.

Qwen3.8-Flash-Next-FP8

Provides FP8-quantized Hugging Face weights and config for Qwen3.8-Flash-Next (block size 128), preserving near-original performance. Compatible with Transformers, vLLM, SGLang and TokenSpeed; intended for efficient deployment of a 125B multimodal causal LM with very long context support.

Ox Alpha - 10k

10,005 single-turn prompts and metadata derived from Ox Alpha chat traces, labeled by category, subcategory, and difficulty. Built for response-teacher generation and distillation workflows, with topic and difficulty distributions to aid dataset curation.

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.

Qwen3.8-Flash-Next

Experimental open-weight multimodal LLM preview designed for long-context, agentic workloads. It introduces hybrid sparse attention (QSA), gated residual streams, and large offloadable n‑gram embeddings (51B) alongside a high-sparsity MoE (125B total, 6B active) to trade memory for runtime efficiency and improved long-horizon reasoning.

EchoWM: Open and Enterable Omnimodal World Models

Generates enterable omnimodal world-model rollouts that follow continuous 6-DoF camera control while jointly producing 720p video, environmental sound, music and speech. Uses dataset-level motion calibration, a specialized data engine, progressive training and autoregressive post-training to support long-horizon first- and third-person interaction.