AI Model2026
Post-trained Qwen3.8-27B variant using the COLD FUSION (GAIN+Unsloth) tuning to reduce internal reasoning-token use and improve instruction following while keeping base capabilities. Deliverables include 256k-context-compatible GGUF quants (regular and MTP, NEO IMATRIX), vision support via an mmproj, and three reasoning-effort modes (xhigh/medium/low).
AI Video Papers2026
Automates evaluation of visual world models via a hierarchical agent pipeline that decomposes each case, spawns specialized sub-agents to collect diagnostic evidence, and outputs a verifiable evidence tree plus a final verdict; validated on 18 models across 330 cases and released as a live evaluation pipeline.
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 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.
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 Model2026
A 35B mixture-of-experts LLM tuned for agentic coding and end-to-end self-improvement: it jointly generates tasks, scaffolds, and solution rollouts. Activates ~3B params/token, supports 256K context (extendable), and emits chain-of-thought plus OpenAI-style tool calls.
AI Video Papers2026
Introduces SemComp-Bench: a benchmark and VLM-based evaluation protocol for measuring outcome achievement and task-relevant semantic grounding in instruction-driven video generation. Ships with SemComp-Data, curated image–instruction–outcome triplets and OA/GR scoring.
AI Model2026
GGUF build of Ornith-1.5's 35B mixture-of-experts model (A3B) for local inference — activates ~3B params per token, supports up to 262,144 tokens, emits separate reasoning traces and OpenAI-style tool calls, optimized for agentic coding and long-context use cases.
AI Model2026
A draft model that predicts whole blocks of tokens in parallel for speculative decoding of Qwen3.8-27B. Uses block-diffusion drafting with per-position candidate sets and a selector plus dynamic convolutions to keep end-of-block accuracy, increasing accepted tokens per verification and end-to-end throughput versus autoregressive decoding.
AI Model2026
An uncensored, weight-modified variant of Qwen3.8-27B that surgically removes the model's refusal directions to produce 0% refusals while aiming to preserve or improve capability. Uses complementary abliteration blending (SVD + LEACE blend) and ships with recommended greedy inference settings; intended for AI-safety research and red‑teaming, not for causing harm.