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

Reinforcement Learning Papers·2026
Icon for item

$N_0$-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens

NeoteAI Team, Fudan TEAI Team

Enables tactile-aware robot manipulation by pretraining a vision–tactile–language–action foundation model and improving offline policies with ALTER. Combines large-scale NeoData visuo-tactile pretraining, a latent tactile pathway for predictive touch signals, and advantage‑conditioned offline RL for contact-rich tasks.

#robotics#rl#foundation-model#multimodal#vision+3
GitHub
AI Client·2026
GitHub

Codex ChatGPT Web

miuuyy

Brings ChatGPT Web models (including Pro) into Codex’s native model picker so you can run Temporary Chats with full Codex task context, images, streaming, and visible tool activity. Provides a desktop launcher and an optional MCP tunnel connector to route ChatGPT tool calls back to the local Codex task (filesystem, shell, tools). Unofficial browser automation that requires a signed-in ChatGPT account and developer-mode connector.

#chatgpt#codex#mcp#mcp-client#chatbot+6
Hugging Face
AI Dataset·2026
Icon for item

LocateAnything-Data

NVEagle (NVlabs / NVIDIA)

Consolidated dataset of detection, visual grounding and pointing annotations with indexed WebDataset image shards and Megatron‑Energon training metadata. Covers diverse visual domains (COCO, RefCOCO, driving, GUI, documents) and uses a normalized spatial grid for cross‑domain vision–language grounding training.

#multimodal#vision#ocr#nvidia#huggingface+3
AI Agent Papers·2026
Icon for item

JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents

Yunlong Lin, Zixu Lin +24

Lets canvas-native agents plan, generate, edit, and organize long-horizon multimodal creative projects by representing artifacts, versions, and actions as typed canvas nodes and links. Uses a three-layer design (canvas state, protocol bridge, agent runtime) so agents act within an inspectable, editable project state.

#multimodal#ai-agent#agent-skills#long-horizon#ai-workflow+2
Hugging Face
AI Model·2026
Icon for item

Kimi K3

reteetzad·Moonshot AI

An open-weight LLM focused on deep reasoning, native agentic tool use, and repository-scale code understanding — Mixture-of-Experts architecture with an extended context window and permissive licensing.

#kimi#foundation-model#LLM#agent-skills#reasoning+2
Hugging Face
AI Model·2026
Icon for item

Inkling-Small

Thinking Machines Lab

Generates text from text, image, or audio inputs using a native multimodal, Mixture-of-Experts autoregressive transformer (276B total / 12B active) with up to 1M-token context; targeted at conversational, agentic, coding and multimodal applications.

#transformers#multimodal#llm#huggingface#benchmarks+4
Hugging Face
AI Model·2026
Icon for item

Kimi K3 (unsloth/Kimi-K3)

unsloth·Moonshot AI, Unsloth

Open-weight multimodal Mixture-of-Experts LLM with native vision and a 1,048,576-token context window. 2.8T parameters (104B activated), MXFP4 quantization, released for agentic long-horizon coding, knowledge work, and vision-in-the-loop workflows.

#multimodal#transformers#vision#vllm#huggingface+7
Large Language Model Papers·2026
Icon for item

Kimi K3: Open Frontier Intelligence

Kimi Team, Tongtong Bai +400

Presents a 2.8T-parameter Mixture-of-Experts multimodal model with a 1-million-token context window and 104 billion activated parameters, targeting long-horizon agentic RL, coding, reasoning, and vision. Key innovations include Kimi Delta Attention, Attention Residuals, Stable LatentMoE (16 of 896 experts active per token), ~2.5× scaling efficiency over Kimi K2, and a public weight release.

#kimi#foundation-model#llm#multimodal#vision+6
Hugging Face
AI Model·2026
Icon for item

unsloth/Kimi-K3-GGUF

unsloth·Moonshot AI, unsloth

GGUF-quantized build of Moonshot AI's Kimi K3 for local inference: MXFP4-aware quantization, image-text-to-text pipeline support, native vision and a 1,048,576-token context window. Intended for local GGUF runtimes (vLLM, SGLang, TokenSpeed) with Kimi K3 license constraints.

#kimi#huggingface#transformers#multimodal#llm+5
Natural Language Processing Papers·2026
Icon for item

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Jiangnan Li, Yuqing Li +3

Turns document relevance into an execution prior for agentic corpus interaction: orders documents for sequential ripgrep traversal, seeds promising entry points with query-relevant paragraphs, and reranks grep matches to surface informative excerpts. Improves the accuracy–efficiency frontier on browse QA and reasoning-intensive retrieval.

#retrieval#RAG#reasoning#LLM#NLP+3
Natural Language Processing Papers·2026
Icon for item

Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory

Ruizhe Li, Mingxuan Du +2

Measures how agent memory systems miss implicitly associated facts by introducing InMind, a 125-task benchmark with paired controls that separate stored-vs-retrieval vs knowledge gaps. Quantifies a large retrieval-interface blind spot and points to routing as the core open problem.

#benchmark#evaluation#paper#LLM#NLP+3
AI Agent Papers·2026
Icon for item

From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search

Junlin Liu, Jiangwang Chen +8·Beijing Institute of Technology, East China Normal University +3

Bridges the proprietary-to-open-source gap in agentic search by converting multi-step retrieval and reasoning traces into a structured, style-normalized JSON protocol and using it for joint distillation + RL. Produces denser supervision that improves student success rates while reducing style drift.

#distillation#agent-skills#RL#LLM#reasoning+5
  • Previous
  • 1
  • More pages
  • 181
  • 182
  • 183
  • More pages
  • 255
  • Next