Free Downloads - Tech News

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

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.

DanceOPD framework overview - composing multiple AI image generation capabilities

AI & Machine Learning

DanceOPD: Composing Multiple AI Image Generation Capabilities Into One Model

By Hunter Io June 27, 2026AI & Machine Learning

DanceOPD is a new on-policy generative field distillation framework that composes T2I, local editing, and global editing into a single flow-matching model using hard-routed field matching.

Agent Memory Systems - Typical Execution Workflows

News

Are We Ready For An Agent-Native Memory System? A Deep Dive Into LLM Agent Memory Architectures

By Hunter Io June 26, 2026News

A comprehensive evaluation of 12 agent memory systems reveals no single architecture dominates all scenarios. Here is what the research found.

Wan-Streamer single Transformer architecture with block-causal attention for audio-visual streaming interaction

AI & Machine Learning

Wan-Streamer: The First End-to-End Real-Time Audio-Visual Foundation Model

By Hunter Io June 26, 2026AI & Machine Learning

Introduction: Beyond Cascaded Systems Current multimodal AI systems are built as cascaded pipelines — separate…

KaLM-Reranker-V1 FBNL framework architecture diagram showing encoder-decoder design

AI & Machine Learning

KaLM-Reranker-V1: A Fast but Not Late Interaction Reranker for Compressed Documents

By Hunter Io June 26, 2026AI & Machine Learning

KaLM-Reranker-V1 introduces Fast But Not Late Interaction (FBNL) for efficient document reranking with Matryoshka Embedding Pooling. Achieves SOTA on BEIR with 10-200x speedup over existing solutions.