Discover the Best AI Resources
Curated essentials, no noise — just what matters
Presents a unified black-box reinforcement learning framework to train and optimize agents running inside complex execution harnesses. Uses sandbox-parallel rollouts, a serving proxy that captures model calls and reconstructs multi-turn trajectories as prefix trees, and adapted GRPO/PPO optimizers to achieve stable, scalable RL across heterogeneous harnesses.
AI Dataset2026
Provides experimental and in-silico data for 1,440 de novo miniprotein binders designed by Anthropic's Claude models, including per-design kinetics, raw sensorgrams, structure-predictions, and design provenance. Includes two independent wet‑lab assessments and extensive per-design files; data released under CC BY 4.0.
Enables interactive serving of large Mixture-of-Experts (MoE) models on personal machines by adapting offload and execution to measured device bandwidth and agentic workload patterns. Key features include bandwidth-adaptive execution, semantic-aware caching of recurrent state, and an elastic GPU expert cache; supports 20+ MoE models and runs models from ~35B to 753B on consumer/workstation GPUs.
AI Agent Papers2026
Enables closed-loop execution for embodied agents by evolving code-based runtime critics and recovery skills online while keeping the base policy frozen. Combines three timescale loops with Z-Infra rollout infrastructure; reports 90.8% on LIBERO-Pro, 93.6% on RoboCasa and an 11.1× inference speedup.
AI Video2026
Upscales Minimax H3 24-channel VAE latents in-place to increase spatial resolution while preserving the time dimension. Replaces the decode→pixel-upscale→encode round-trip with a learned 2D/3D latent upscaler to save compute and avoid interpolation ghosting; supports 1.0–4.0× scaling.
AI Model2026
Injects proprietary news, regulatory and legal data into an open checkpoint via data-centric continual learning to improve performance on legal, tax and journalism tasks while preserving general capabilities and very long context support.
AI Agent Papers2026
Evaluates whether AI systems can independently carry out project-level scientific research by progressively removing human methodological guidance across 60 tasks in 11 domains. Built with expert review, sandbox execution, and multi-agent–model scoring to measure innovation and autonomous experimental execution.
AI Model2026
A 9B open-weight reasoning LLM that uses a self-improvement loop to auto-generate tasks, construct scaffolds, and optimize rollouts for stronger agentic coding and long-context reasoning. Single-GPU deployable, supports tool-calling and a 262,144-token context window.
AI Model2026
Provides an abliterated (refusal-removed) build of Qwen3.8-27B for offline research and red‑teaming, keeping multimodal vision, an MTP speculative head, and a 262,144-token context. It has no built-in safety guardrails and is released under Apache‑2.0 for research use only.
Uses cooperative multi-agent RL where multiple decoupled models provide peer-derived pseudo-rewards to each other, enabling unsupervised improvements in reasoning; increases cohort diversity to reduce correlated errors and avoid training collapse, showing consistent gains across text and multimodal benchmarks.
AI Audio2026
Generates and edits speech from natural-language instructions plus optional reference audio, supporting zero-shot TTS, content/acoustic/paralinguistic edits, enhancement, and source separation. Open-source 1.5B-parameter base model with a 4-step distilled AuK‑Flash for faster inference.
Embodied AI2026
Turns embodied navigation into 2D visual prompting where a vision-language model selects image pixels that are projected to 3D actions; adds selective chain-of-thought, compressed anchor-trajectory memory, and a two-level alignment objective to improve sample and runtime efficiency.