AIAIAny
  • Search
  • Collection
  • Category
  • Tag
  • Daily AI
AIAIAny

Discover the Best AI Resources

Curated essentials, no noise — just what matters

AIAIAny

Curated AI Resources for Everyone

[email protected]

Powered by airss.app

Product
  • Search
  • Collection
  • Category
  • Tag
Resources
  • Blog
Company
  • Privacy Policy
  • Terms of Service
  • Sitemap
Copyright © 2026 All Rights Reserved.

Contents

Hugging Face
AI Dataset·2026
Icon for item

CodeVideoBench

Code Video Model Team, Microsoft Research

Provides 22 curated Three.js-based cases for code-guided video generation across eight application categories. Each case bundles an editable scene (Three.js program), a 960×544 proxy video, a 1536×864 reference image, and a plain-text prompt for controlled video-generation evaluation.

#video#datasets#benchmarks#ai-video#javascript+3
Hugging Face
AI Audio·2026
Icon for item

yue2-mothersuperior-realaudio-tokenizer-v4

Mothersuperior

Encodes real audio into YuE2 semantic tokens and ships a matching NAR-branch LoRA so the YuE2 decoder renders realistic latents—enables tokenizing recordings, training artist LoRAs, and generating songs or covers. Includes an 8-layer tokenizer head and a rank-32 decoder LoRA; requires the YuE2 base models and GPU resources.

#audio#lora#huggingface#safetensors#pytorch+3
GitHub
AI Agent·2026
Icon for item

Elephant-Goldfish Model (EGM)

Google

Have a context-aware assistant draft software specifications, then send them to fresh-context agents to uncover missing assumptions and implementation risks. Human developers retain the final design decisions and approval.

#plugin#agent-skills#coding-agents#software-engineering#ai-agent+1
GitHub
AI Agent·2026
Icon for item

Jakeschincariol/instagram-agent-skill

Jake Schincariol

Breaks Instagram content work into 13 Claude workflows for Reels, research, captions, and planning. It produces drafts for your approval; it does not post or operate your account.

#agent-skills#ai-agent#claude#claude-code#github
Hugging Face
AI Model·2026
Icon for item

EmbeddingGemma 2

Google DeepMind

Generates unified 768‑dimensional embeddings for text (including code), images, video and audio to enable cross‑modal semantic search and retrieval. Supports task instruction prefixes, Matryoshka truncation to 128/256/512/768 dims, and modular encoders for on‑device use under an Apache‑2.0 license.

#embeddings#multimodal#gemma#google#huggingface+10
AI Agent Papers·2026
Icon for item

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

Meiduo Chong, Shaolei Zhang +2

Provides a self-evolving ontology layer that enables LLM-based data agents to query and interact with heterogeneous data via an MCP server; it auto-builds and iteratively refines schema, content, and tool layers based on agent interactions.

#mcp-server#mcp#ai-agent#agent-skills#llm+5
Reinforcement Learning Papers·2026
Icon for item

Bellman Policy Optimization

Zhuoqing Song, Haotian Xu +2·Apodex US, Inc., Princeton University

Reframes Policy Mirror Descent for autoregressive LLM generation into a critic-free, trajectory-level objective using the Bellman equations to avoid per-token value estimation. Derives a practical token-level loss with a smoothed mismatch-correction weight and shows improved math-reasoning accuracy on benchmarks.

#rl#LLM#reasoning#paper#qwen+3
AI Agent Papers·2026
Icon for item

Atria Dawn: The Dawn of Agentic Superintelligence

Honglin Guo, Tao Gui +141

Presents Atria Dawn Preview, an agentic foundation LLM trained with a Verifiable Experience Pipeline to connect tool-mediated interactions to executable environments; evaluated across 16 real-world research and engineering benchmarks with top scores on five, and a human–AI collaboration analysis of 769 task records.

#foundation-model#LLM#agent-skills#ai-agent#benchmark+1
Hugging Face
AI Model·2026
Icon for item

Qwen-Image-2.1

Qwen

Unified text-to-image and prompt-based image editing model that natively outputs RGBA and accepts up to 10 reference images. Compact 7B visual generator optimized for 2K outputs and efficient inference; research-licensed under the Qwen Research License.

#qwen#diffusers#safetensors#ai-image#image+3
AI Agent Papers·2026
Icon for item

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Tong Zheng, Xidong Wu +15·Affiliation: \thepa, Affiliation: University of Maryland, College Park +2

Turns past discovery traces into replayable simulators so alternative exploration policies can be evaluated offline ('dreaming'), enabling fast, low-cost meta-level policy improvement for agent-driven discovery across coding, optimization, and GPU-kernel tasks.

#ai-agent#agent-skills#coding-agents#long-horizon#world-model+8
AI Model·2026

Jev

Diogo Almeida

Explains how Jev turns input state into typed decisions and probabilities without generating text. Introduces parallel sampling and RLCD training, with workflow evaluations and caveats for software automation.

#blog#ai-inference#ai-workflow#rl#ai-api
Natural Language Processing Papers·2026
Icon for item

RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation

ZhuoXin Liu, Zhiming Ma +11

Benchmarks joint recovery of obfuscated platform messages and evidence-grounded web investigations by pairing 3,600 synthetic restoration inputs with 600 controlled web environments. Separately scores message-entry recovery and downstream web risk judgments, and provides a frozen multimodal evidence judge plus a resettable local sandbox for reproducible agent evaluation.

#benchmarks#evaluation#NLP#multimodal#agent-skills+2
  • Previous
  • 1
  • More pages
  • 215
  • 216
  • 217
  • More pages
  • 256
  • Next