Large language models for code (LLM4Code) have greatly improved developer productivity but also raise privacy concerns due to their reliance on open-source repo...
Future AI systems could conceal their capabilities ('sandbagging') during evaluations, potentially misleading developers and auditors. We stress-tested sandbagg...
Qubit readout is a critical operation in quantum computing systems, which maps the analog response of qubits into discrete classical states. Deep neural network...
Embedding a language field in a 3D representation enables richer semantic understanding of spatial environments by linking geometry with descriptive meaning. Th...
We propose Multi-view Pyramid Transformer (MVP), a scalable multi-view transformer architecture that directly reconstructs large 3D scenes from tens to hundreds...
We present GRAPE (Group RepresentAtional Position Encoding), a unified framework for positional encoding based on group actions. GRAPE brings together two famil...
Storytelling in real-world videos often unfolds through multiple shots -- discontinuous yet semantically connected clips that together convey a coherent narrati...
LLM-based agents are rapidly being plugged into expert decision-support, yet in messy, high-stakes settings they rarely make the team smarter: human-AI teams of...
Carbon-aware schedulers aim to reduce the operational carbon footprint of data centers by running flexible workloads during periods of low carbon intensity. Mos...
We introduce a new paradigm for building large causal models (LCMs) that exploits the enormous potential latent in today's large language models (LLMs). We desc...
Large language models (LLMs) are increasingly deployed in settings where reasoning, such as multi-step problem solving and chain-of-thought, is essential. Yet, ...
Stream processing is a computing paradigm that supports real-time data processing for a wide variety of applications. At Meta, it's used across the company for ...
