Find the idea.
Understand the evidence.
Research perspectives and practical workflow proposals across industries. Explore what has been studied, what is still uncertain, and how to test a useful first project.
Before you build an agent team, define one good workflow.
A practical way to choose between fixed workflows, tool-using agents, and specialist teams—starting with a decision your business can actually verify.
Read the perspectiveAgent architecture
Scroll to explore
Operations blueprint
Scroll to explore
Procurement agents should build the evidence before the shortlist.
How to turn quotes, delivery constraints and approval policies into a traceable comparison—without letting a model invent the winning supplier.
A healthcare scheduling agent needs a state machine, not a promise.
A careful administrative blueprint for proposed appointments, resource checks and staff confirmation, grounded in the FHIR scheduling model.
Commerce agents have to respect inventory truth.
Why available stock, reserved units and location matter more than a convincing sales reply—and how to design an exception workflow around them.
Let a solver plan routes. Let an agent explain the exceptions.
A logistics blueprint that separates constraint solving from conversational coordination, so proposed plans remain feasible and inspectable.
Running a pilot in your own cloud: exactly what IT has to do
Network paths, secrets, SSO, logging, data residency, and roll-back when ProcureAI or FinanceAI workers run in your account instead of a public trial.
Research to practice
Scroll to explore
From language to robot action: the boundary that matters.
What OpenVLA shows about learned robot policies, and why a first business pilot should separate task planning from physical execution.
Research agents should make hypotheses easier to challenge.
What Co-Scientist and ChemCrow suggest about tool-assisted research, and a proposed evidence workflow that preserves uncertainty and expert review.
Connected systems
Scroll to explore
Manufacturing agents need machine context before machine control.
A read-only incident-assistance blueprint that joins equipment signals with manuals and maintenance history, while keeping control boundaries clear.
Adding agents next to Coupa without re-platforming
Which Coupa objects to read first, where ProcureAI agents sit in the AP loop, what buyers see during a pilot, and how to scope read-only access before any write-back.
Read-only first: connecting agents to SAP S/4HANA
How to scope OData read access, stage sandbox mapping, run a batch pilot, and defer hold codes or invoice blocks until your AP organisation signs off.
Healthcare finance teams: agents that never touch the EHR
How hospital AP and shared services use ProcureAI on supplier invoices and POs today, what data stays out of clinical systems, and what a future clinical-adjacent agent would still refuse to do. HIPAA compliance is not offered by Stellitron today.
From the analysis archive
Research summary · sources listed
These earlier research summaries remain available for exploration. Sources and publication notes are on each article page; claims belong to the original authors. Proposed workflows are illustrations to evaluate, not customer deployments.
The Cell Ontology in the age of single-cell omics: Analysis of The Cell Ontology in the age of single-cell omics
Single-cell omics technologies have transformed our understanding of cellular diversity by enabling high-resolution profiling of individual cells. However, the unprecedented scale and heterogeneity of...
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm
"Thinking with Text" and "Thinking with Images" paradigm significantly improve the reasoning ability of large language models (LLMs) and Vision Language Models (VLMs). However, these paradigms have in...
SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs
Extreme low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance degradation at 2-bits and even 4-bits (e.g., MXFP4). We present SignRoundV2, a post-training…
Qwen3-VL Technical Report
We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens,…
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following
Large language models excel at interpreting complex natural language instructions, enabling them to perform a wide range of tasks. In the life sciences, single-cell RNA sequencing (scRNA-seq) data ser...
From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
Artificial intelligence (AI) is reshaping scientific discovery, evolving from specialized computational tools into autonomous research partners. We position Agentic Science as a pivotal stage within t...
Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
Latent Diffusion Models (LDMs) inherently follow a coarse-to-fine generation process, where high-level semantic structure is generated slightly earlier than fine-grained texture. This indicates the preceding semantics potentially benefit…
ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction: Analysis of ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models (VLMs), trained lar...
Invasive species, extreme fire risk, and toxin release under a changing climate: Analysis of Invasive species, extreme fire risk, and toxin release under a changing climate
Mediterranean ecosystems such as those found in California, Central Chile, Southern Europe, and Southwest Australia host numerous, diverse, fire-adapted micro-ecosystems. These micro-ecosystems are as...
DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
Real-world enterprise data intelligence workflows encompass data engineering that turns raw sources into analytical-ready tables and data analysis that convert those tables into decision-oriented insights. We introduce DAComp, a benchmark…
Byzantine-Resilient SGD in High Dimensions on Heterogeneous Data
We study distributed stochastic gradient descent (SGD) in the master-worker architecture under Byzantine attacks. We consider the heterogeneous data model, where different workers may have different l...
ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning
Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to use tools for verification, limiting their reliability on…
Light-X: Generative 4D Video Rendering with Camera and Illumination Control
Recent advances in illumination control extend image-based methods to video, yet still facing a trade-off between lighting fidelity and temporal consistency. Moving beyond relighting, a key step toward generative modeling of real-world…
RAE: Analysis of bytetriper/RAE
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration: Analysis of Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration
Diffusion models have achieved impressive generative quality across modalities like 2D images, videos, and 3D shapes, but their inference remains computationally expensive due to the iterative denoisi...
SAM 3: Segment Anything with Concepts
We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., "yellow school bus"), image exemplars,…
LiveAvatar: Analysis of Alibaba-Quark/LiveAvatar
Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"
dKV-Cache: The Cache for Diffusion Language Models: Analysis of dKV-Cache: The Cache for Diffusion Language Models
Diffusion Language Models (DLMs) have been seen as a promising competitor for autoregressive language models. However, diffusion language models have long been constrained by slow inference. A core ch...
Foundations of GenIR: Analysis of Foundations of GenIR
The chapter discusses the foundational impact of modern generative AI models on information access (IA) systems. In contrast to traditional AI, the large-scale training and superior data modeling of g...
What does it mean to understand language?: Analysis of What does it mean to understand language?
Language understanding entails not just extracting the surface-level meaning of the linguistic input, but constructing rich mental models of the situation it describes. Here we propose that because pr...
When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models
Frontier large language models (LLMs) such as ChatGPT, Grok and Gemini are increasingly used for mental-health support with anxiety, trauma and self-worth. Most work treats them as tools or as targets of personality tests, assuming they…
AutoNeural: Co-Designing Vision-Language Models for NPU Inference
While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrates. We attribute this hardware-model mismatch to two…
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 are as follows: (1) DeepSeek Sparse Attention (DSA): We…
Structured Extraction from Business Process Diagrams Using Vision-Language Models
Business Process Model and Notation (BPMN) is a widely adopted standard for representing complex business workflows. While BPMN diagrams are often exchanged as visual images, existing methods primarily rely on XML representations for…