Related papers: Probing 3D Chromatin Structure Awareness in Evo2 D…
To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it to visual elements and actions in the environment. This problem is called…
Large language models applied to vast biological datasets have the potential to transform biology by uncovering disease mechanisms and accelerating drug development. However, current models are often siloed, trained separately on…
In order to navigate complex traffic environments, self-driving vehicles must recognize many semantic classes pertaining to vulnerable road users or traffic control devices. However, many safety-critical objects (e.g., construction worker)…
With the rapid advancement of semiconductor technology, Electronic Design Automation (EDA) has become an increasingly knowledge-intensive and document-driven engineering domain. Although large language models (LLMs) have shown strong…
The correct ego-motion estimation basically relies on the understanding of correspondences between adjacent LiDAR scans. However, given the complex scenarios and the low-resolution LiDAR, finding reliable structures for identifying…
The observation of electronic phase separation textures in vanadium dioxide (VO2), a prototypical electron-correlated oxide, has recently added new perspectives on the long standing debate about its metal-insulator transition and its…
Remarkable progress in 2D Vision-Language Models (VLMs) has spurred interest in extending them to 3D settings for tasks like 3D Question Answering, Dense Captioning, and Visual Grounding. Unlike 2D VLMs that typically process images through…
Despite the success of large vision and language models (VLMs) in many downstream applications, it is unclear how well they encode compositional information. Here, we create the Attribution, Relation, and Order (ARO) benchmark to…
Understanding how language models develop their internal computational structure is a central problem in the science of deep learning. While susceptibilities, drawn from statistical physics, offer a promising analytical tool, their full…
A multitude of measures have been proposed to quantify the similarity between protein 3-D structure. Among these measures, contact map overlap (CMO) maximization deserved sustained attention during past decade because it offers a fine…
Foundation models for biology and physics optimize predictive accuracy, but their internal representations systematically fail to preserve the continuous geometry of the systems they model. We identify the root cause: the Geometric…
Recently exciting progress has been made on protein contact prediction, but the predicted contacts for proteins without many sequence homologs is still of low quality and not very useful for de novo structure prediction. This paper presents…
DNA foundation models have become transformative tools in bioinformatics and healthcare applications. Trained on vast genomic datasets, these models can be used to generate sequence embeddings, dense vector representations that capture…
This paper addresses the challenges in representation learning of 3D shape features by investigating state-of-the-art backbones paired with both contrastive supervised and self-supervised learning objectives. Computer vision methods…
The potential of deep learning has been recognized in the protein structure prediction community for some time, and became indisputable after CASP13. In CASP14, deep learning has boosted the field to unanticipated levels reaching…
Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…
Vision foundation models, particularly the ViT family, have revolutionized image understanding by providing rich semantic features. However, despite their success in 2D comprehension, their abilities on grasping 3D spatial relationships are…
End-to-end autonomous driving has gained significant attention for its potential to learn robust behavior in interactive scenarios and scale with data. Popular architectures often build on separate modules for perception and planning…
Recent advances in applying deep learning in genomics include DNA-language and single-cell foundation models. However, these models take only one data type as input. We introduce dynamic token adaptation and demonstrate how it combines…
Recent advances in language model interpretability have identified circuits, critical subnetworks that replicate model behaviors, yet how knowledge is structured within these crucial subnetworks remains opaque. To gain an understanding…