MIT CSAIL

Phenalene's detection in a VeLLO environment reveals a surprising fourfold abundance increase compared to other PAHs, challenging existing notions of PAH distribution in the interstellar medium.

Most enzyme specificity models fail to outperform basic sequence alignment methods, highlighting a critical gap in predictive capabilities.

DiscoPER not only automates hypothesis generation but also self-analyzes its discoveries, revealing hidden patterns and expanding the search space in unprecedented ways.

NNPs can achieve near-chemical accuracy in enzyme catalysis predictions with less than 1,000 system-specific data points, revolutionizing the efficiency of mechanistic studies.

A unified platform for molecular machine learning that supports 100 elements and incorporates uncertainty quantification could democratize access to advanced chemical property predictions.

Machine learning can transform 2DES by extracting maximum insights from limited data while guiding experimental design for improved accuracy.

Current AI agents excel in structured tasks but falter at generating novel insights and tackling open-ended scientific challenges.

Gradient inference can revolutionize how we tackle gradient estimation in complex probabilistic programs, enabling new state-of-the-art estimators that outperform traditional methods.

Active exploration can dramatically enhance adults' ability to reason about complex causal relationships, but even with this advantage, they still struggle compared to simpler tasks.

Coordinating AI agents across scientific disciplines only boosts performance when each discipline captures a unique piece of the puzzle, otherwise, simpler combined summaries often suffice.

Quantum kernels unlock signal in medical image embeddings where classical methods fail, suggesting a new path for extracting value from medical foundation models.

Imagine slashing the human effort needed to go from hypothesis to submission-ready ML theory paper by orders of magnitude.

Automated identification of individual animals can only be effective if it aligns with ecological questions and data practices, not just algorithmic accuracy.

Imagine a medical "Google" where you can search for similar patients using text, images, and medical history, and predict future health risks years in advance – Apollo brings this closer to reality.

You can boost medical image super-resolution fidelity by over 3dB just by swapping in a domain-specific VAE, no fancy diffusion architecture needed.

Exact robust regression at scale is now possible: a new algorithm solves the NP-hard Least Trimmed Squares problem orders of magnitude faster than existing methods.

EquiformerV3 achieves state-of-the-art performance in atomistic modeling by combining architectural improvements with optimized software, enabling accurate energy-conserving simulations.

Forget simulating backward dynamics: solve stochastic optimal control problems by just watching the system relax forward.

Finally, a large, diverse, and experimentally-anchored dataset of transition metal complex DFT properties is available to fuel ML model development and DFT benchmark studies.

LLM agents can autonomously outperform fixed evolutionary search by 3-10x on open-ended discovery tasks when given persistent memory, asynchronous collaboration, and heartbeat-based interventions.

Hyperpolarizing the nuclear spin bath surrounding a molecular qubit can significantly extend its coherence time, offering a new knob for quantum control.

Rényi divergence may be the missing key to understanding thermal equilibrium in quantum systems, revealing a novel constraint on wavefunction ensembles.

Heuristic maritime routes lead to extreme fuel waste in nearly 5% of voyages, but this RL approach cuts that risk by almost 10x.

Neural networks can accurately predict polymer free energies, even when traditional methods like Bennett Acceptance Ratio fail due to poor phase-space overlap.

Lattice QCD calculations just got a whole lot faster: normalizing flows slash variance by up to 60x in key observables.

E(3)-equivariant networks just got a whole lot faster: a new algorithm cuts the complexity of Clebsch-Gordan Tensor Products from $O(L^6)$ to $O(L^4\log^2 L)$ without sacrificing completeness.

Ditch the geometry-to-property map: this work uses the external potential as the primary input for machine learning models, unlocking a scalable and equivariant approach to predicting electronic structure.

Injecting spatial transcriptomics data into existing pathology foundation models unlocks significant performance gains across a range of downstream tasks, including molecular status prediction and gene-to-image retrieval.

Self-supervised learning beats supervised learning for ECG interpretation when labeled data is scarce, unlocking more robust and generalizable AI-driven cardiac diagnostics.