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

Machine Learning Engineering Papers·2026
Icon for item

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Junlin Yang, Che Jiang +22

Autonomously proposes, modifies, executes, and evaluates ML experiments to study recursive self-improvement in machine learning engineering. Implements an open stack (OpenMLE-Gym, -RL, -Evo) and post-trains Frontis-MA1 (35B) around four evolution operators (Draft, Improve, Debug, Crossover); releases model weights and the full codebase.

#paper#code#github#mlops#ai-agent+4
AI Agent Papers·2026
Icon for item

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Hanzhang Zhou, Panrong Tong +14

Designs and evaluates a foundation GUI agent that performs cross-platform GUI and CLI actions on real devices to complete long-horizon workflows. Emphasizes a unified action space, a large-scale real-device mobile runtime, an AutoResearch-style data flywheel, and online RL training across 10,000+ concurrent environments.

#qwen#ai-agent#agent-skills#mobile#android+6
Hugging Face
AI Dataset·2026
Icon for item

Fable-5 Premium Dataset

Sai Dutta Abhishek Dash·Hugging Face, Crownelius collection

A cleaned supervised fine-tuning dataset of 6,365 Claude Fable-5 agent traces in OpenAI Chat and Hugging Face agent-traces formats, prepared for SFT, tool-use training, and distillation workflows; MIT-licensed and distributed as Parquet.

#huggingface#claude#llm#parquet#polars+3
Computer Vision Papers·2026
Icon for item

VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

Kangning Zhang, Yixing Li +10

Estimates the visually attributable portion of a privileged teacher’s next-token corrections and reconstructs student-anchored training targets for multimodal on-policy distillation. Uses counterfactual teacher queries and a signed proxy to raise supported tokens and suppress refuted ones, improving fine-grained visual knowledge transfer across model scales.

#distillation#multimodal#vision#benchmark#paper+2
Large Language Model Papers·2026
Icon for item

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

Xiangning Lin, Shenzhe Zhu +24

Introduces AISPA, a user-centric framework to audit system prompts in LLM applications, and applies it to 3,249 instructions from 88 commercial products to classify protective versus problematic instructions. Highlights design variability, growing prompt length/protection, persistent problematic directives, and calls for transparency and oversight.

#paper#prompt-engineering#LLM#evaluation#privacy+1
Reinforcement Learning Papers·2026
Icon for item

QQWorld: Quantile-Quantile Matching for World Model Regularization

Zhoushun Yu, Xiaoyu Hu +1

Regularizes latent world models by replacing the Epps–Pulley Gaussianization objective with a quantile–quantile matching loss that aligns projected latent samples to rank-matched Gaussian quantiles, improving tail correction and planning success via cross-batch ranking.

#RL#paper#long-horizon#robotics#vision+1
AI Agent Papers·2026
Icon for item

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Qiushi Sun, Kanzhi Cheng +21·The University of Hong Kong, Xi’an Jiaotong University +4

Evaluates vision-language model judges on computer-using agent (CUA) trajectories to measure verifier reliability. Provides OSReward-Hard and OSReward-Multi challenge sets, the OS-Shepherd-100K reasoning-annotated corpus, and trained OS-Shepherd reward models that match commercial judges at ~30–60× lower cost.

#evaluation#benchmark#benchmarks#vision#multimodal+4
AI Agent Papers·2026
Icon for item

MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations

Qiming Shi, Yulong Tao +11

A 365-day, order-level simulation benchmark for evaluating long-term coherence of LLM agents in seller-side e-commerce. Grounded in 98,843 real product records and 26 interactive tools, it pairs prompt upstream supplier signals with delayed downstream order outcomes to stress planning, memory, and tool use over long horizons.

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

Kroma v0.1

lodestones

Provides a single-file ComfyUI-compatible LoRA plus full-weight RMSNorm/modulation .diff deltas that reproduce a Krea 2 fine-tune when applied to Krea 2 checkpoints. Rank-256 adapters, ~1.88 GB, MIT-licensed.

#lora#huggingface#diffusers#ai-image#qwen
Hugging Face
AI Model·2026
Icon for item

DeepSeek-V4-Flash-0731

DeepSeek-AI

An OpenAI-compatible LLM checkpoint optimized for agentic and long-context scenarios, shipping DSpark speculative decoding and vLLM/SGLang deployment recipes; tailored for code-agent and multi-step reasoning workloads and released under MIT.

#deepseek#transformers#llm#agent-skills#coding-agents+5
AI Agent Papers·2026
Icon for item

DarwinX: Evolving Agent Harnesses Through Natural Selection

Yifan Zhang, Yutong Dai +10·Affiliation: Salesforce AI Research, Affiliation: Salesforce Agentforce

Treats agent self-improvement as natural selection over a population of harnesses (prompts, tools, skills, control flow), evolving a frozen-model agent by selecting harness edits that extend capability without regressing others. Uses a preserve-and-extend contract, lineage archive, and verifier-driven fitness (no gold solutions) to recombine complementary edits and transfer across benchmarks.

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

DeepSeek-V4-Flash-0731-GGUF

unsloth, DeepSeek-AI

Enables local use of a GGUF-quantized DeepSeek-V4-Flash-0731 via Unsloth Dynamic quantizations; provides a Q8 (162GB) lossless option and smaller Q4 variants for lower-memory inference and agentic scenarios using Unsloth tooling.

#deepseek#huggingface#llm#benchmarks#coding-agents+3
  • Previous
  • 1
  • More pages
  • 185
  • 186
  • 187
  • More pages
  • 259
  • Next