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

GitHub
AI Agent·2026
Icon for item

AgenticOS

Vstorm

Build, share and govern company AI agents on infrastructure you control, connecting them to internal documents and tools. Roles, budgets, approvals and run records add operational oversight; hosted and local models are supported.

#ai-agent#ai-infra#ai-workflow#RAG#mcp
GitHub
AI Infra·2026
Icon for item

kimi-k3-in-c

Fareed Khan

Runs Kimi K3 inference on CPU by streaming model weights from storage instead of keeping them all in RAM. The project reports 8.24 GB peak memory, with substantially slower token generation at low-memory settings.

#ai-inference#cpu#ai-infra#ai-development#code+6
AI Agent Papers·2026
Icon for item

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Yunhao Chen, Xin Wang +7·Affiliation: Fudan University, Affiliation: Shanghai Artificial Intelligence Laboratory +1

Evolves persistent, stateful environments to red-team tool-using AI agents — provides 10K+ validated scenarios across 50 domains and a feedback-driven attack policy (EMHA) to surface long‑horizon safety failures.

#paper#benchmark#evaluation#agent-skills#long-horizon+4
Hugging Face
AI Model·2026
Icon for item

LFM2.5-2.6B-GGUF

LiquidAI

Provides a GGUF-quantized, llama.cpp-compatible build of LiquidAI's LFM2.5-2.6B for local CPU inference and offline deployment. Supports multilingual generation and long-context workflows; optimized for low-memory, on-device use.

#llama.cpp#llm#multilingual#huggingface#cpu+4
Speech Technology Papers·2026
Icon for item

Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval

Ilia Semenkov, Daria Kleeva +3

Retrieves short speech segments from MEG recordings with a compact interpretable neural decoder trained against wav2vec 2.0 embeddings, and maps decoder weights to cortical source space to reveal which acoustic and linguistic features drive retrieval.

#paper#speech#audio#retrieval#embeddings+1
Hugging Face
AI Model·2026
Icon for item

BigBang-V1

endless-frontier

Finetunes Qwen3.6‑35B using an adversarial generator–critic loop that synthesizes ~10,000 verifiable “frontier” tasks to boost scientific research, long‑horizon reasoning, coding and tool use; supports an extended 262,144‑token context and common serving stacks.

#qwen#llm#transformers#vllm#huggingface+6
Hugging Face
AI Model·2026
Icon for item

Mach-1 Additive 35B

SyzygyResearch

A 35B additive ternary-quantized variant of Mach-1 that aims to preserve most capabilities of its BF16 teacher while reducing compute and memory; shows ~95% mean retention across 12 benchmarks and competitive per-task parity on several evaluations.

#qwen#llm#foundation-model#benchmarks#huggingface+2
Hugging Face
AI Model·2026
Icon for item

MiniMax-H3 GGUFs

realrebelai

Provides GGUF-quantized, ComfyUI-ready MiniMax‑H3 model files (FL2VA/REF2VA, text encoder, audio/video VAEs) to enable local ComfyUI inference for short video + stereo audio generation; requires the official VAEs and sufficient VRAM.

#multimodal#video#audio#huggingface#diffusers+4
Computer Vision Papers·2026
Icon for item

Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing

Junliang Ye, Kenkun Liu +13·Tencent

Provides a unified multimodal framework for large-scale 3D understanding, text-to-3D generation, and instruction-guided 3D editing. Trains on an 87M-sample 3D multimodal corpus (25M understanding, 50M generation, 12M editing) and pairs a vision-language model with a diffusion-based 3D synthesizer to preserve structure and enable part-aware edits; suited for researchers building text-driven 3D asset pipelines but requires large compute and data.

#multimodal#vision#ai-image#AIGC#foundation-model+2
Machine Learning Engineering Papers·2026
Icon for item

Knowledge-Geometry Decoupling: Refreshable Pretrained Transfer for Streaming Recommendation

Zixuan Wang, Yuhong Chen +11·[email protected], [email protected] +3

A pretrain-then-transfer method for streaming recommendation that decouples refreshable behavioral knowledge from task-specific geometry to enable continual model refresh without downstream interference; introduces Behavioral Multi-Token Prediction and Anchored Calibration Residual and shows 4–12% offline gains plus live Shopee A/B lifts.

#paper#foundation-model#embeddings#benchmarks#code+5
Hugging Face
AI Model·2026
Icon for item

Qwen3-VL-32B Ultra Uncensored Heretic — MiniMax-H3 ComfyUI INT8 ConvRot

ethanfel

Provides ComfyUI-ready INT8 MiniMax‑H3 checkpoints (conditioning encoder plus optional generation tail) for a Heretic-edited Qwen3‑VL‑32B source; preserves the vision tower in BF16 and uses row-wise ConvRot INT8 quantization to reduce VRAM needs for ~32GB GPUs. Not a full Transformers generation repository.

#huggingface#qwen#llm#multimodal#pytorch+4
Reinforcement Learning Papers·2026
Icon for item

Progressive Agent Skill Generation via Reinforcement Learning

Junhao Shen, Zhanqiu Zhang +2

Frames skill generation as a sequential editing task and introduces a novel rollback reward to train an RL generator (Skill-α) that evaluates each edit by its downstream execution impact, producing skills that improve agent success rates across document-to-skill and experience-to-skill settings.

#agent-skills#RL#rl#llm#evaluation+3
  • Previous
  • 1
  • More pages
  • 186
  • 187
  • 188
  • More pages
  • 259
  • Next