YC startup offers $1M for materials science AI challenges
Discovered Materials is offering $1 million for solutions to five unsolved problems in materials science that frontier AI models have failed to crack.
Stories per day · 30 days
2 RSS
Relatedagentic-ai1ai-challenge1benchmarks1crystal-generation1crystal-structure-prediction1deepsci-reasoner1diffusion-models1forecasting1generative-models1grain-boundaries1large-language-models1machine-learning-potentials1neural-networks1open-problems1physical-constraints1scientific-ml1semiconductors1simulation1
13 stories, newest first · one card per story
Stories tagged #materials-science
AI forecasts grain growth under non-isothermal conditions
Recurrent neural networks conditioned on thermal data predict grain growth with mean relative errors below 5%.
TCSP3.0 fixes composition errors and lifts crystal prediction match rates
On T180, Top-1 rises from 28.3% to 72.2%, beating CrystalFlow and MaskGXT even before relaxation.
DeepSciReasoner predicts scientific spectra under physical constraints
Evaluations cover eDOS, phonon density of states, XANES and Raman spectra, with no numeric accuracy deltas given.
Orbitol generates crystals constrained to requested space groups
On MP-20, 13.8% of attempts stayed stable or metastable, unique, novel, and in the requested group after relaxation.
GBClaw agentic framework studies nickel grain boundary deformation
On 14 asymmetric tilt boundaries, misfit dislocations were tied to large differences in shear strength.
Opus 5.5 agents discover two room-temperature magnetic semiconductor candidates
Opus 5.5 agents identified two room-temperature magnetic semiconductor candidates, including unmade YBaMnFeO5.
A self-learning scientific agent for X-ray diffraction
Gan Jiang, a self-learning XRD agent, outperforms expert skills and leads DeltaXRDbench phase identification.
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents
AutoSciBench automatically generates scientific-agent benchmarks that lower solver accuracy versus human-curated tests.
EP-Flow: Disordered Crystal Structure Prediction without Site-Level Annotations
EP-Flow predicts disordered crystal structures from formulas without site-level disorder labels.
Retrainable physics-integrated neural differentiable modeling of sintering across material systems
Sinter-PiNDiff predicts ceramic density and grain growth from sparse data across three material systems.
Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model
A hybrid diffusion-adversarial model generates heterogeneous 3D geological microstructures from cheap 2D images, replacing denoising loss with adversarial loss for stable training.
Building the materials foundation for AI
Syensqo's CTO says AI pushes semiconductors and data centers to physical limits, driving advanced materials demand and AI-accelerated materials discovery.
5