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

AI Agent Papers·2026
Icon for item

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Hejia Geng, Zesen Huang +43

Transforms scientific code repositories into executable, agent-learnable environments that support task generation, execution, and scientific verification. Agent-guided repository transformation produces verified interaction trajectories used to train the PhAI-IDE model family. Intended for research on agent learning, scientific-code repair, and training RL/SFT models.

#ai-agent#agent-skills#IDE#science#code+7
AI Agent Papers·2026
Icon for item

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

Jeonghye Kim, Minseon Kim +6·KAIST, Microsoft Research Montréal +1

Extracts replayable behaviors from working web apps and converts them into verifiable, reference-guided software-engineering tasks to evaluate and diagnose coding agents; includes an automated pipeline that scales to thousands of tasks.

#benchmark#coding-agents#software-engineering#evaluation#programming+2
Reinforcement Learning Papers·2026
Icon for item

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Yizhuo Li, Jianhao Yan +10

Analyzes a failure mode in PPO critics called “Value Flattening” and proposes SP³O (Sparse PPO), which supervises a small set of well-separated states per response to mitigate flattened value estimates and improve policy learning for LLM alignment and reasoning tasks.

#rl#LLM#qwen#paper#research+1
Computer Vision Papers·2026
Icon for item

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

Ji Xie, Dewei Zhou +3

Enables specifying exact 24-bit hex colors for object-level image generation and editing via a unified prompt interface, using a Paint-500K dataset and timestep-gated pure-color anchors to improve color fidelity.

#paper#vision#ai-image#prompt-engineering#benchmark+2
Large Language Model Papers·2026
Icon for item

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Anyi Xu, B. Li +115

Describes DeepSeek-V4.1-Flash, a 552B-parameter multimodal Mixture-of-Experts LLM that supports up to 1M-token contexts and reduces KV cache footprint using Compressed Sparse Attention 2, FP4 KV caching, and SWA Bounded Replay to lower HBM/SSD and prefill costs.

#deepseek#moe#fp4#multimodal#long-horizon+3
Hugging Face
AI Model·2026
Icon for item

Ming-Image-0.1-Design

inclusionAI, Ant Group

Generates complete UI, poster and infographic layouts from text prompts, rendering legible in-image text and producing native RGBA output with transparent backgrounds. Suited for text-rich visual design workflows and pairs with a companion model that decomposes designs into editable layers.

#diffusers#safetensors#ai-image#image#huggingface+4
Large Language Model Papers·2026
Icon for item

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Yuxiao Yang, Tianrun Yu +7

Analyzes why on-policy distillation can produce excessively long student rollouts by identifying termination-token mismatch between students and teachers, and proposes aggregating functionally equivalent EOS tokens as a shared semantic stopping action to mitigate length inflation.

#distillation#qwen#gemma#llm#nlp+3
AI Agent Papers·2026
Icon for item

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Haozhe Liu, Tian Ye +12

Finds token- and API-cost-saving harness mechanisms for long-horizon coding agents using automated recursive self-improvement; packages four surviving mechanisms (action fusion, context compaction, observation archiving, delegated reading) to cut recorded token traffic ~44.7–49.0% and API cost by about one third while preserving most capability.

#coding-agents#long-horizon#agent-skills#pi#research+6
AI Agent Papers·2026
Icon for item

An Empirical Study of Harness Design for Coding Agents

Run-Ze Fan, Zihao Zhang +7

Measures how individual harness components—planning, action space, and context management—affect coding agents' success, cost, and behavior. Uses a modular harness across 176 matched settings on SWE-Bench Verified and Terminal-Bench 2.1 to isolate component effects and surface model- and budget-dependent trade-offs.

#coding-agents#evaluation#benchmarks#long-horizon#software-engineering+4
Machine Learning Foundation Papers·2026
Icon for item

JEPA-Anything: Learning Predictive Models across Different Worlds

Taoyong Cui, Zhongyao Wang +11

Provides a domain-agnostic world-modeling framework that factorizes latent targets into orthogonal predictive components, with dedicated prediction branches and synthesis for multi-domain forecasting and intervention. Demonstrates improved dynamics and long-horizon rollouts across seven domains and includes experimental biological validation.

#paper#world-model#research#long-horizon#biology+5
AI Agent Papers·2026
Icon for item

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

Shuai Bai, Jiayong Deng +30

Provides reproducible, multi‑platform environments and execution‑grounded verification for hybrid computer‑use agents that interleave GUI exploration and code/CLI. Key features: a five‑platform harness, RecreationBench (250 tasks), reference‑grounded programmatic and visual assertions for automatic scoring.

#coding-agents#agent-skills#ai-agent#benchmarks#evaluation+3
Hugging Face
AI Dataset·2026
Icon for item

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Haolin He, Yunfei Chu +16·The Chinese University of Hong Kong, Alibaba Token Hub, Alibaba Group +3

Provides a complete benchmark and training release for native audio‑visual dialogue: 2,800 synthesized audio‑visual dialogues, tiered rubrics, scoring code, ~28GB of 1080p media, and an RL reward recipe to evaluate and train omni models that take video+audio and return text.

#multimodal#audio#video#benchmark#evaluation+6
  • Previous
  • 1
  • More pages
  • 218
  • 219
  • 220
  • More pages
  • 261
  • Next