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

Tag

Explore by tags

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.
  • All

  • 30u30

  • ASR

  • ChatGPT

  • GNN

  • IDE

  • RAG

  • agent-skills

  • ai

  • ai-agent

  • ai-api

  • ai-api-management

  • ai-client

  • ai-coding

  • ai-demos

  • ai-deploy

  • ai-development

  • ai-framework

  • ai-image

  • ai-image-demos

  • ai-inference

  • ai-infra

  • ai-leaderboard

  • ai-library

  • ai-rank

  • ai-security

  • ai-serving

  • ai-tools

  • ai-train

  • ai-video

  • ai-workflow

  • AIGC

  • algorithms

  • alibaba

  • amazon

  • android

  • annotated-cif

  • anthropic

  • arabic

  • audio

  • aws

  • benchmark

  • benchmarks

  • bf16

  • biology

  • biomolecular-design

  • blender

  • blog

  • book

  • bun

  • bytedance

  • chatbot

  • chatgpt

  • chemistry

  • claude

  • claude-code

  • cli

  • clickhouse

  • code

  • codex

  • coding

  • coding-agents

  • comfyui

  • common-crawl

  • copilot

  • course

  • cpu

  • cuda

  • cursor

  • datasets

  • deepmind

  • deepseek

  • depth

  • desktop

  • devops

  • diffusers

  • distillation

  • distributed-systems

  • dna

  • docker

  • drug-discovery

  • dsh

  • dsh-plugin

  • edge

  • egocentric

  • electron

  • embeddings

  • embodied-ai

  • engineering

  • evaluation

  • facebook

  • finance

  • flow-matching

  • foundation

  • foundation-model

  • fp4

  • fp8

  • gcode

  • gcp

  • gemini

  • gemini-cli

  • gemma

  • genomics

  • gguf

  • gitHub

  • github

  • go

  • google

  • gpu

  • gradient-booting

  • grok

  • groq

  • gsq

  • heretic

  • hermes

  • huggingface

  • hy_v4

  • image

  • image-to-code

  • imatrix

  • imu

  • ios

  • java

  • javascript

  • json

  • kimi

  • kotlin

  • kubernetes

  • laion

  • llama.cpp

  • LLM

  • llm

  • long-horizon

  • lora

  • mLOps

  • manipulation

  • math

  • mcap

  • mcp

  • mcp-client

  • mcp-server

  • meta

  • meta-ai

  • meta-pytorch

  • metal

  • microsoft

  • mixture-of-experts

  • mlops

  • mlx

  • mobile

  • mocap

  • moe

  • multilingual

  • multimodal

  • muse

  • muse-spark

  • mysql

  • navigation

  • nli

  • NLP

  • nlp

  • nodejs

  • numpy

  • nvfp4

  • nvidia

  • ocr

  • ollama

  • onnx

  • openai

  • opencode

  • pandas

  • paper

  • parquet

  • physical-reasoning

  • physics

  • pi

  • plugin

  • plugins

  • polars

  • postgres

  • prefix-caching

  • privacy

  • programming

  • prompt-engineering

  • protein

  • protein-design

  • pruning

  • pwa

  • python

  • pytorch

  • quantization

  • qwen

  • rco

  • react

  • reasoning

  • red-teaming

  • redis

  • refactoring

  • renders

  • reranker

  • research

  • retrieval

  • RL

  • rl

  • robotics

  • routing

  • rust

  • safetensors

  • science

  • security

  • segmentation

  • sft

  • shodan

  • skillkit

  • slam

  • software-engineering

  • sora

  • speech

  • sqlite

  • ssh

  • structural-biology

  • stt

  • supabase

  • swe

  • swift

  • synthetic

  • tensorrt

  • terminal

  • text-generation

  • text-to-code

  • thinking

  • threejs

  • trae

  • training-data

  • transformers

  • translation

  • tts

  • turkish

  • tutorial

  • typescript

  • unsloth-dynamic

  • vibe-coding

  • video

  • vision

  • visual-to-code

  • vllm

  • voice

  • vue

  • vulkan

  • vultr

  • web-search

  • webdataset

  • windsurf

  • world-model

  • writing

  • xAI

  • xai

  • youtube

Hugging Face
AI Dataset·2026
Icon for item

SharpaDex v1.0

Sharpa Robotics

Multimodal real-robot dataset of 28,993 teleoperated bimanual manipulation demonstrations (~300 hours) with synchronized multi-view RGB/tactile videos, 65D robot state/action, 60D fingertip tactile signals, and temporally aligned language segments; intended for imitation, visuomotor and visual‑tactile research, CC BY‑NC 4.0 (non‑commercial).

#robotics#embodied-ai#multimodal#datasets#video+5
AI Agent Papers·2026
Icon for item

AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

Hongjin Qian, Chaofan Li +12·Beijing Academy of Artificial Intelligence (BAAI)

Defines and evaluates AREX-2, an LLM agent that iteratively self-improves at test time via reflection and long-horizon execution. Trained on long-horizon improvement trajectories from ML engineering and algorithmic programming (built on Qwen3.8-27B), it scales with more rounds and achieves strong benchmark scores.

#agent-skills#long-horizon#qwen#LLM#benchmarks+3
Large Language Model Papers·2026
Icon for item

Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It

Zehao Jin, Ruixuan Deng +1·Georgia Institute of Technology

Demonstrates that pretrained transformers typically use only ~1–3 lines of depth to follow reference chains, and that a task‑trained rank‑8 LoRA applied at one early layer (with all other weights frozen) can extend reference‑following to dozens or hundreds of lines while adding only a few ten‑thousand parameters.

#lora#qwen#transformers#LLM#NLP+4
AI Video Papers·2026
Icon for item

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

Hui Ren, Lei Fan +6·University of Illinois Urbana-Champaign, Amazon.com, Inc.

Groups visually grounded appearances of the same physical instance into persistent, retrievable “biographies” so agents can follow objects across hours or days for long-video question answering. Links identity-aware observations to episodic context and visual evidence; improves EgoLifeQA to 72.0% and increases evidence-window reach from 37.6% to 58.9%.

#video#vision#multimodal#long-horizon#retrieval+2
AI Video Papers·2026
Icon for item

FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation

Bo Yin, Xiaobin Hu +2·National University of Singapore, Harbin Institute of Technology (Shenzhen)

Predicts compact 'prospective tokens' that summarize upcoming information needs and uses them to select a small set of past frames for conditioning long-horizon video generation, improving long-range consistency, visual quality, and action alignment while remaining plug-and-play across diverse generators.

#video#ai-video#long-horizon#world-model#vision+4
AI Agent Papers·2026
Icon for item

Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States

Yu Luo, Jiamin Jiang +10·Nankai University, Alibaba Group +1

Constructs and continually maintains explicit belief states for long-horizon LLM agents, combining a structured world estimate with unresolved epistemic and achievement gaps. Adds consistency validation, Belief Trapping detection, and tailored recovery to improve execution and diagnosis benchmarks.

#long-horizon#LLM#ai-agent#agent-skills#benchmarks+3
Hugging Face
AI Model·2026
Icon for item

Kolibri-1

Aleph Alpha GmbH, Aleph Alpha Research GmbH

Processes English and German text with long-context reasoning and structured tool-calling. Uses a 78B mixture-of-experts architecture that activates ~3.46B parameters per token, offers native 262k-token context (validated to 1M), and is released as Apache-2.0 weights — suited for RAG, document processing and human-in-the-loop decision support.

#moe#vllm#fp8#safetensors#reasoning+10
AI Video Papers·2026
Icon for item

Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency

Sixun Dong, Wei Li +5·University of Central Florida, Meta Reality Labs +1

Introduces LoHi, a training-free, single-pass method that mixes dense low-resolution video streams with sparse high-resolution frames to improve long-video vision-language model accuracy under strict token budgets while cutting front-end decoding latency.

#video#vision#multimodal#ai-video#paper+4
Large Language Model Papers·2026
Icon for item

ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience

Haodong Lu, Dong Gong·University of New South Wales (UNSW Sydney)

Adapts LLM agents online by self-distilling verified execution trajectories into persistent LoRA weights during deployment to improve success and efficiency on long‑horizon tasks. Uses a frozen stable copy as a privileged teacher to predict hindsight next‑token distributions and filters invalid-action turns so experience consolidates without external solutions or memory retrieval.

#LLM#long-horizon#distillation#lora#agent-skills+4
Large Language Model Papers·2026
Icon for item

From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

Quanyu Long, Xiao Chen +5·Nanyang Technological University, The Hong Kong Polytechnic University

Converts historical interaction traces into a reusable, queryable “worldbook” and runs a language-based world model agent (Trace2Env) as the environment for LLM agents — enabling stateful, grounded simulation with improved next-observation fidelity and long-horizon consistency.

#world-model#ai-agent#LLM#long-horizon#benchmark+3
AI Agent Papers·2026
Icon for item

nanoMuse: An Open-Source Personal Agent for Every Device You Own

Guangyi Liu, Yong Liu +1

Runs an open-source personal software agent across a user's devices to perform actions, keep readable provenance-backed memories, and coordinate via a self-hostable relay. Ships minimal end-to-end clients (mobile, desktop, web) under GPL-3.0; model-agnostic and designed for inspectability and device

#ai-agent#agent-skills#github#paper#mcp-server+10
Large Language Model Papers·2026
Icon for item

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

Xin Wang, Hao Yu +10·Affiliation: Alibaba Token Hub, Alibaba Group, Affiliation: Ohio State University

Proposes TRACE, an FP4 quantization framework for RL of MoE LLMs that uses rollout-side FP4 outcomes to guide training-side rounding and caches mantissa/scale from deeper layers to limit overhead. Preserves BF16-level RL performance while enabling up to 5.4× rollout speedup.

#fp4#quantization#moe#RL#LLM+4
  • Previous
  • 1
  • More pages
  • 13
  • 14
  • 15
  • More pages
  • 18
  • Next