Free Downloads - Tech News

HiFi-UMI project website screenshot showing robot-free data collection system

HiFi-UMI: Zero-Robot Post-Training for Manipulation Policies

By Hunter Io July 30, 2026AI & Machine Learning, Tech news

HiFi-UMI proves robot-free UMI data alone can match teleoperation for post-training manipulation policies — 3mm accuracy, zero real-robot data needed.

AI & Machine Learning

Kimi K3: The Open-Source 2.8T MoE Model That Rethinks Attention

By Hunter Io July 29, 2026AI & Machine Learning

Kimi K3: The Open-Source 2.8T MoE Model That Rethinks Attention On July 27, 2026, Moonshot…

AI & Machine Learning

SLAI T-Rex: Post-Training DeepSeek-V4 on Ascend NPUs

By Hunter Io July 24, 2026AI & Machine Learning

SLAI T-Rex achieves 34.22% MFU post-training DeepSeek-V4 on Ascend 910C NPUs. Learn how AuraKernel, parallelism, and OR specialization enabled a 2.93x improvement.

AI & Machine Learning Open Source

AgentDebugX: Debug LLM Agents Like a Pro — Open-Source Toolkit for Failure Observability, Attribution & Recovery

By Hunter Io July 24, 2026AI & Machine Learning, Open Source

Debug LLM agents like a pro with AgentDebugX — an open-source, MIT-licensed toolkit that closes the debugging loop: Detect → Attribute → Recover → Rerun. DeepDebug pinpoints root causes with 28.8% accuracy on Who&When benchmark and repairs 13 of 73 failed GAIA tasks in a single rerun.

DeepSearch-World paper thumbnail from Hugging Face - self-distillation framework for web agents

AI & Machine Learning

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

By Hunter Io July 22, 2026AI & Machine Learning

HKUST's DeepSearch-Evolve trains 9B web agents to improve through self-distillation—no teacher needed. 61.5% on GAIA, 93.4% on HotpotQA, fully open-source.

AI & Machine Learning

Ornith-1.0: Open-Source Self-Improving Models for Agentic Coding

By Hunter Io June 30, 2026AI & Machine Learning

Ornith-1.0 is a self-improving open-source model family achieving state-of-the-art performance on agentic coding benchmarks. Available in 9B, 35B, and 397B variants with MIT license.

ProMSA - Progressive Multimodal Search Agent for Visual Question Answering

News

ProMSA: Smart AI Search Agent for Visual Question Answering

By Hunter Io June 30, 2026News

ProMSA is a progressive multimodal search agent that helps AI answer knowledge-based visual questions by smartly searching images and text on Wikipedia.

DeepSpec GitHub Repository showing DSpark speculative decoding framework by DeepSeek

AI & Machine Learning

DeepSeek DSpark Explained: How Speculative Decoding Makes V4 Up to 85% Faster

By Hunter Io June 29, 2026AI & Machine Learning

Learn how DeepSeek DSpark uses speculative decoding to accelerate V4 inference by up to 85%. Open-source framework with lossless quality preservation.

ConAct framework showing context management as part of the action space for mobile GUI agents

AI & Machine Learning

MemGUI-Agent: End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management

By Hunter Io June 28, 2026AI & Machine Learning

MemGUI-Agent is an end-to-end mobile GUI agent using ConAct framework for proactive context management, achieving 62.5% Pass@3 on MemGUI-Bench with an 8B trained model.