arXiv
Verdict: NotableCoworkOS:Scaling Agent Coworkers for Real-world Automation
Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts.
- HF ▲ 78
- Stars ★ 46
Artificial Intelligence
Models, methods, and the machinery of intelligence.
Edition No. 36
Updated UTC
Top stories
1. HairDeck: Animation-Ready Stylized Hair Cards from a Single Image
The hair of stylized characters in games and avatars is built from hair cards: artist-placed ribbons whose geometry is the visible hair, animated by spring bones.
Verdict: Notable█████░░░░░5.22. PhotoGuider: Composition-Aware Cropping and 360^° View Framing with Explainable Photographic Assessments
Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop.
Verdict: Notable█████░░░░░5.0
More top stories
- arXivby Fan, He, Jiang +3
CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents
Across coding, web, and tool-use tasks, language-model agents are now routinely trained with the same recipe: supervised fine-tuning (SFT) to learn the interface, then multi-turn ....
No.03Verdict: NotableScore█████░░░░░4.5 - arXivby Wu, Huang, Ho +3
RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory
Recent work shows that a frozen robot policy performs far better inside an agent harness, where control code decides when to query the policy, consult vision tools, or command the arm ....
No.04Verdict: NotableScore████░░░░░░4.2 - arXivby Maser, Gairola, Rao +1
Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers
Foundational vision models have become the de facto standard for many vision tasks due to their strong performance.
No.05Verdict: NotableScore████░░░░░░4.2 - arXivby Hu, Wang, Talwar +3
DR Pixel: Page-Native Deep Research with Vision-Language Models
Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to ....
No.06Verdict: NotableScore████░░░░░░4.2 - arXivby Wu, Pappu, Zou +6
Measuring AI Agents as Teammates with Collaborative Intelligence
Progress in AI is often measured by what a single model can do on its own.
No.07Verdict: NotableScore████░░░░░░4.2 - arXivby Metinov, Arziev
Glance: The Generator Is Its Own Reranker
Retrieval-augmented generation commonly serves separate models for reranking and answering, duplicating model residency and passage processing.
No.08Verdict: NotableScore████░░░░░░4.1
Briefs
- arXiv
DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
████░░░░░░4.0 - arXiv
KlaskTron: An Open-Source Platform for Physical Adversarial Multi-Agent RL
████░░░░░░4.0 - arXiv
SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding
████░░░░░░4.0 - arXiv
RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild
████░░░░░░4.0 - arXiv
TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation
████░░░░░░4.0 - arXiv
VLM-as-a-Judge for Person Re-Identification
████░░░░░░4.0 - arXiv
MirrorComm: A Communication-Efficient Cooperative Perception Framework via Mirrored World Models
████░░░░░░3.9 - arXiv
Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement
████░░░░░░3.9 - arXiv
Data-Scarce, Multi-Granular, Multimodal: Benchmark Design for Biosynthetic Gene Clusters
████░░░░░░3.9 - arXiv
TSB-SEG: A Systematic Time-Series Segmentation Benchmark
████░░░░░░3.9