arXiv:2602.10195v1 Announce Type: new
Abstract: A novel sequence architecture design is introduced, Versor, which uses Conformal Geometric Algebra (CGA) in place of the traditional fundamental non-linear operations to achieve structural generalization and significant performance improvements on a v...
Adaptive Optimization via Momentum on Variance-Normalized Gradients
arXiv:2602.10204v1 Announce Type: new
Abstract: We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two complementary ideas: variance-based normalization and momentum applied after normalization. MVN-Grad sc...
AI reads brain MRIs in seconds and flags emergencies
Researchers at the University of Michigan have created an AI system that can interpret brain MRI scans in just seconds, accurately identifying a wide range of neurological conditions and determining which cases need urgent care. Trained on hundreds of thousands of real-world scans along with patient...
Lagged backward-compatible physics-informed neural networks for unsaturated soil consolidation analysis
arXiv:2602.07031v1 Announce Type: new
Abstract: This study develops a Lagged Backward-Compatible Physics-Informed Neural Network (LBC-PINN) for simulating and inverting one-dimensional unsaturated soil consolidation under long-term loading. To address the challenges of coupled air and water pressur...
Somewhere between “this model will replace your entire workflow” and “this chatbot will become your best friend,” many teams are left wondering what’s real, what’s useful, and what’s just… very confident marketing.
That’s where Stability AI stands out.
In Silicon Valley, OpenAI has built systems and infrastructure that allow experimentation to turn into durable engineering outcomes (not fragile prototypes held together by hope and a README), and the world can’t get enough…
Scientists create smart synthetic skin that can hide images and change shape
Inspired by the shape-shifting skin of octopuses, Penn State researchers developed a smart hydrogel that can change appearance, texture, and shape on command. The material is programmed using a special printing technique that embeds digital instructions directly into the skin. Images and information...
MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitation
arXiv:2602.05048v1 Announce Type: new
Abstract: Joint planning through language-based interactions is a key area of human-AI teaming. Planning problems in the open world often involve various aspects of incomplete information and unknowns, e.g., objects involved, human goals/intents -- thus leading...
VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learning
Video-conditioned sound and speech generation, encompassing video-to-sound (V2S) and visual text-to-speech (VisualTTS) tasks, are conventionally addressed as separate tasks, with limited exploration to unify them within a signle framework. Recent attempts to unify V2S and VisualTTS face challenges i...
How PARTs Assemble into Wholes: Learning the Relative Composition of Images
The composition of objects and their parts, along with object-object positional relationships, provides a rich source of information for representation learning. Hence, spatial-aware pretext tasks have been actively explored in self-supervised learning. Existing works commonly start from a grid stru...
Building AI in healthcare is hard enough without fighting your own data systems. In Austin, Takeda is tackling that problem head-on, creating a platform designed for scale, compliance, and real-world impact.
Active Epistemic Control for Query-Efficient Verified Planning
arXiv:2602.03974v1 Announce Type: new
Abstract: Planning in interactive environments is challenging under partial observability: task-critical preconditions (e.g., object locations or container states) may be unknown at decision time, yet grounding them through interaction is costly. Learned world ...
As global banking collides with AI at scale, Citi is quietly rebuilding its core from Austin. What’s emerging is a blueprint for how the next generation of finance gets engineered. Ready to join the future of global banking?
arXiv:2602.02500v1 Announce Type: new
Abstract: The Newton-Schulz (NS) iteration has gained increasing interest for its role in the Muon optimizer and the Stiefel manifold. However, the conventional NS iteration suffers from inefficiency and instability. Although various improvements have been intr...
Sparse Adapter Fusion for Continual Learning in NLP
arXiv:2602.02502v1 Announce Type: new
Abstract: Continual learning in natural language processing plays a crucial role in adapting to evolving data and preventing catastrophic forgetting. Despite significant progress, existing methods still face challenges, such as inefficient parameter reuse acros...
Learning ORDER-Aware Multimodal Representations for Composite Materials Design
arXiv:2602.02513v1 Announce Type: new
Abstract: Artificial intelligence (AI) has shown remarkable success in materials discovery and property prediction, particularly for crystalline and polymer systems where material properties and structures are dominated by discrete graph representations. Such g...
PeerRank: Autonomous LLM Evaluation Through Web-Grounded, Bias-Controlled Peer Review
arXiv:2602.02589v1 Announce Type: new
Abstract: Evaluating large language models typically relies on human-authored benchmarks, reference answers, and human or single-model judgments, approaches that scale poorly, become quickly outdated, and mismatch open-world deployments that depend on web retri...
Representation Learning Enhanced Deep Reinforcement Learning for Optimal Operation of Hydrogen-based Multi-Energy Systems
arXiv:2602.00027v1 Announce Type: new
Abstract: Hydrogen-based multi-energy systems (HMES) have emerged as a promising low-carbon and energy-efficient solution, as it can enable the coordinated operation of electricity, heating and cooling supply and demand to enhance operational flexibility, impro...