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

Large Language Model Papers·2026
Icon for item

DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space

Jiangwang Chen, Zixin Song +11·Tsinghua University, Qwen Business Unit of Alibaba +2

Co-evolves a solver skill and a rubric-generator skill for text-space LLM optimization under decoupled objectives to avoid rubric gaming without using gold rubrics. Solver updates use criterion-level feedback; generator updates use independent audits of requirement coverage and response discrimination.

#LLM#evaluation#agent-skills#qwen#paper+2
Reinforcement Learning Papers·2026
Icon for item

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Bo-Wen Zhang, Junwei He +6

Allocates token-level credit in rubric-conditioned GRPO by counterfactually replaying the same response under rubric and criteria-free prompts, using tokenwise log-likelihood contrasts to compute bounded, response-normalized weights that redistribute GRPO advantages without training an auxiliary scorer.

#RL#LLM#NLP#paper#evaluation
Hugging Face
AI Dataset·2026
Icon for item

ASI-Bench Generated Instances (Seed 42)

Apexintelligence-AI

Provides fixed-seed benchmark instances (prompts and agent-visible inputs) for ASI-Bench to run reproducible evaluations of LLM agents on scientific tasks. Includes four matched prompt levels (B1–B4) across 60 project-level tasks in 11 domains; excludes reference answers and private scorers; Apache-2.0 licensed.

#benchmark#benchmarks#evaluation#ai-agent#agent-skills+4
Computer Vision Papers·2026
Icon for item

CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition

Lai Wei, Chengqi Li +4

Evaluates multimodal context learning across grounding, new information application, and knowledge acquisition using a 3,443-instance benchmark spanning science, finance, long documents, spatial reasoning, and web VQA; finds current multimodal models perform poorly (best score 0.2847) and analyzes failure modes.

#multimodal#benchmark#vision#evaluation#paper+4
GitHub
AI Agent·2026
Icon for item

LoopForge

Tencent

Orchestrates coding agents through repeatable software delivery workflows, with sandboxed workspaces, human approval gates, and run history. Teams can use chat for exploratory work or standardize proven processes as SOPs.

#coding-agents#ai-agent#ai-coding#ai-workflow#docker+1
Computer Vision Papers·2026
Icon for item

ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

Jooyeol Yun, Jintae Park +4

Recovers editable design files from raster images by growing an editable layer hierarchy via an agentic pipeline that selects and composes modality-specific tools. Introduces graceful verification (accept/prune/retry) to prevent error accumulation and presents the Figma Edit Replay Benchmark (909 files, 14,796 edits) to measure editability across layout, color, and text edits.

#vision#image#multimodal#paper#benchmark+3
Hugging Face
AI Dataset·2026
Icon for item

ACE-Data-0

Yukang Cao, Haozhe Xie +14·S-Lab, Nanyang Technological University, Singapore, ACE Robotics

Captures synchronized multimodal embodied-human data in real homes — egocentric and multi-view video, metric body/hand/object motion, audio, and tactile signals. Released under a gated non-commercial research license with identifiable participants and strict non-redistribution/privacy constraints.

#video#robotics#multimodal#audio#long-horizon+3
Hugging Face
AI Dataset·2026
Icon for item

ASI-Bench Generated Instances (Seed 31415)

Apexintelligence-AI

Generated instance set (seed 31415) for ASI‑Bench: includes four matched prompt variants, agent-visible inputs, reference artifacts, and instance metadata for 60 project-scale scientific research tasks across 11 domains; intended for evaluating autonomous research agents. Licensed Apache‑2.0.

#benchmark#benchmarks#ai-agent#agent-skills#research+4
GitHub
AI Coding·2026
Icon for item

AI Design Skills

Provides reusable design rules for AI coding tools, covering page structure, copy, and visual styling. Skills are distributed as standalone Markdown files that work across multiple coding assistants.

#agent-skills#ai-coding#coding-agents
Hugging Face
AI Audio·2026
Icon for item

NVIDIA NemotronLabs VoiceChat 11B

NVIDIA

An end-to-end 11B full-duplex speech model for real-time conversational AI that jointly performs streaming speech understanding and generation, enabling ~450 ms turn-taking, barge‑in and live tool calling in a single unified architecture; research use only.

#nvidia#huggingface#voice#speech#ASR+6
Machine Learning Foundation Papers·2026
Icon for item

Metis: Memory Foundation Model

Zeyu Zhang, Ziliang Guo +15

Presents Metis, a prototype memory foundation model that embeds a persistent native memory state into the backbone so historical experience is compressed and accessed via memory attention. Key features: forward-only, gradient-free online memory updates; memory-specific mid-training objectives; and a dual text/code memory design.

#foundation#llm#ai-agent#agent-skills#multimodal+3
AI Video Papers·2026
Icon for item

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Haodong Li, Tianfei Ren +26

Converts text prompts into physically consistent videos by synthesizing executable Blender programs as a process-level chain-of-thought and using a dual-engine pipeline (deterministic simulation draft + draft-conditioned video editor). Ships with a VideoCoCo-3K draft–instruction–target dataset and shows substantial gains in physical-consistency benchmarks.

#video#ai-video#code#coding#coding-agents+5
  • Previous
  • 1
  • More pages
  • 183
  • 184
  • 185
  • More pages
  • 256
  • Next