Explore public work
Follow a paper to its source byline and saved directory connections.
- 2 OLMo 2 Furious
- A Free Lunch in Generating Datasets: Building a VQG and VQA System with Attention and Humans in the Loop
- A Generalized Training Approach for Multiagent Learning
- A hybrid approach to Internet connectivity for mobile ad hoc networks
- A model-based approach to ongoing product evaluation
- A Multi-Modal Approach to Infer Image Affect
- A novel deringing method based on MAP image restoration
- Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
- Activity Recognition from On-Body Sensors: Accuracy-Power Trade-Off by Dynamic Sensor Selection
- Beyond Sally-Anne: Evaluating Theory of Mind in LLMs using Epistemic Schelling Points
- Cast Vehicle Shadow Segmentation Based on Contour Analysis
- Closing the Gap in the Capacity of Wireless Networks Via Percolation Theory
- Comply/Constrain Subtraction
- Computationally Designed Armadillo Repeat Proteins for Modular Peptide Recognition
- Control-Based Scheduling in a Distributed Stream Processing System
- Convolutional Neural Networks for Sentence Classification
- Dagwood
- Deep learning
- Deployment of Customized Deep Learning based Video Analytics On Surveillance Cameras
- Depthwise Separable Convolutions for Neural Machine Translation
- Description-Driven Task-Oriented Dialog Modeling
- Dynamics of Social Interactions in a Network Game
- Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions
- EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection
- Estimating Q(s,s') with Deep Deterministic Dynamics Gradients
- EuroBERT: Scaling Multilingual Encoders for European Languages
- Evaluation of retrieval-based QA on QUEST-LOFT
- FAST-PPR: Scaling Personalized PageRank Estimation for Large Graphs
- Generative Adversarial Networks
- Gerrymandering and computational redistricting
- Good abandonment in mobile and PC internet search
- Gradient-based learning applied to document recognition
- Holistic Evaluation of Text-To-Image Models
- Human-level Atari 200x faster
- Improved sparse multivariate polynomial interpolation algorithms
- JPEG Anti-Forensics With Improved Tradeoff Between Forensic Undetectability and Image Quality
- Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping
- Learning deep structured semantic models for web search using clickthrough data
- Learning representations by back-propagating errors
- Legibility and predictability of robot motion
- Local Matching Networks for Engineering Diagram Search
- MLGO: a Machine Learning Guided Compiler Optimizations Framework
- MMR
- Modeling Service-Oriented Context Processing in Dynamic Body Area Networks
- Modelling of Current Percolation Channels in Emerging Resistive Switching Elements
- Modularity and interactions in the genetics of gene expression
- Monte Carlo EM for Deep Time Series Anomaly Detection
- Mouse sets
- MultiPoint
- NeMo: A Platform for Neural Modelling of Spiking Neurons Using GPUs
- NIXT: A NCCL Inspector Exporter Tool for Observability of Collective Communication in Large Model Training
- Noise Reduction by Diffusional Dissipation in a Minimal Quorum Sensing Motif
- NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
- Object-Centric Learning with Slot Attention
- Offline Reinforcement Learning with Implicit Q-Learning
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- People tracking using hybrid Monte Carlo filtering
- Perceiver IO: A General Architecture for Structured Inputs & Outputs
- Playing Atari with Deep Reinforcement Learning
- Put: language-based interactive manipulation of objects
- RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation
- Remote Agent: to boldly go where no AI system has gone before
- Renormalization Group for Mixed Fermion-Boson Systems
- Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review
- Sanity Checks for Saliency Maps
- Scalable Extraction of Training Data from (Production) Language Models
- Scaling Generative Recommendations with Context Parallelism on Hierarchical Sequential Transducers
- Scaling Vision Transformers
- Semi-Supervised Kernel Mean Shift Clustering
- Sequence to Sequence Learning with Neural Networks
- Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
- Solving systems of nonlinear polynomial equations faster
- STaR: Bootstrapping Reasoning With Reasoning
- TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action
- The largest countable inductive set is a mouse set
- Transmission over arbitrarily permuted parallel Gaussian channels
- TSNLP - Test Suites for Natural Language Processing
- Universal Intelligence: A Definition of Machine Intelligence
- Visibility culling using hierarchical occlusion maps
- Word Representations via Gaussian Embedding