Research Papers Institution
A research university with strong work in theoretical computer science, machine learning, and systems.
Theorem Proving · Princeton University
LeanDojo turns retrieval-augmented theorem proving in Lean into a concrete research object, with evidence anchors, method tradeoffs, and limits for practical use.
Text Embeddings · Princeton University
SimCSE turns contrastive sentence embedding learning into a concrete research object, with evidence anchors, method tradeoffs, and limits for practical use.
Brain Decoding · Princeton University
MindEye maps fMRI activity into CLIP-like spaces for retrieval and diffusion reconstruction, showing state-of-the-art retrieval and image reconstruction on NSD.
VLM3 shows a standard 4B vision-language model matches expert 3D models — 0.904 depth accuracy, 94.0% camera-pose AUC, 91.35% object-3D accuracy — with no 3D-specific architecture, only focal unification and scaling.
LLM Reasoning · Princeton University
ReAct interleaves a model's reasoning traces with task actions like search and API calls, cutting chain-of-thought hallucination and beating RL agents on ALFWorld by 34% absolute with one or two examples.
Sequence Modeling · Carnegie Mellon University
Mamba makes state space model parameters depend on the input, so it selectively remembers or forgets tokens. It scales linearly, runs 5x faster than Transformers, and Mamba-3B matches Transformers twice its size.