Silvio Savarese

CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments NAACL 2025 xLAM: A Family of Large Action Models to Empower AI Agent Systems NAACL 2025 LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback ACL 2025 PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data ACL 2025 Text2Data: Low-Resource Data Generation with Textual Control AAAI 2025 LATTE: Learning to Think with Vision Specialists EMNLP 2025 ActionStudio: A Lightweight Framework for Data and Training of Large Action Models EMNLP 2025 ViUniT: Visual Unit Tests for More Robust Visual Programming CVPR 2025 SlackAgents: Scalable Collaboration of AI Agents in Workspaces EMNLP 2025 Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D EMNLP 2025 Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents ICLR 2025 Reward-Guided Speculative Decoding for Efficient LLM Reasoning ICML 2025 MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models EMNLP 2025 Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts ICML 2025 CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models NAACL 2025 PRACT: Optimizing Principled Reasoning and Acting of LLM Agent EMNLP 2024 ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding CVPR 2024 HIVE: Harnessing Human Feedback for Instructional Visual Editing CVPR 2024 DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI EACL 2024 "X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-modal Reasoning" ECCV 2024 On the Unlikelihood of D-Separation PGM 2024 Causal Layering via Conditional Entropy CLEAR 2024 PRACT: Optimizing Principled Reasoning and Acting of LLM Agent CONLL 2024 Unified Training of Universal Time Series Forecasting Transformers ICML 2024 Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization ICLR 2024 How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations ICLR 2024 MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens NIPS 2024 OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments NIPS 2024 APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets NIPS 2024 INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness NIPS 2024 CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis ICLR 2023 Masked Unsupervised Self-training for Label-free Image Classification ICLR 2023 ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding CVPR 2023 Procedure-Aware Pretraining for Instructional Video Understanding CVPR 2023 BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models ICML 2023 Modeling Dynamic Environments with Scene Graph Memory ICML 2023 Long Document Summarization with Top-down and Bottom-up Inference EACL 2023 An Extensible Multi-modal Multi-task Object Dataset with Materials ICLR 2023 UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild NIPS 2023 LAVIS: A One-stop Library for Language-Vision Intelligence ACL 2023 Merlion: End-to-End Machine Learning for Time Series JMLR 2023 Best-k Search Algorithm for Neural Text Generation ACL 2023 JRDB-Act: A Large-Scale Dataset for Spatio-Temporal Action, Social Group and Activity Detection CVPR 2022 CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning NIPS 2022 Local calibration: metrics and recalibration UAI 2022 BEHAVIOR-1K: A Benchmark for Embodied AI with 1,000 Everyday Activities and Realistic Simulation CORL 2022 ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation RSS 2022 Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training EMNLP 2022 Discovering Generalizable Skills via Automated Generation of Diverse Tasks RSS 2021 Topological Planning With Transformers for Vision-and-Language Navigation CVPR 2021 BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments CORL 2021 Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration CORL 2021 Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation CORL 2021 Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation CORL 2021 What Matters in Learning from Offline Human Demonstrations for Robot Manipulation CORL 2021 iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks CORL 2021 Adaptive Procedural Task Generation for Hard-Exploration Problems ICLR 2021 TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild ICCV 2021 Goal-Aware Prediction: Learning to Model What Matters ICML 2020 Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation CORL 2020 GTI: Learning to Generalize across Long-Horizon Tasks from Human Demonstrations RSS 2020 Which Tasks Should Be Learned Together in Multi-task Learning? ICML 2020 Leveraging Pretrained Image Classifiers for Language-Based Segmentation WACV 2020 Generative Sparse Detection Networks for 3D Single-shot Object Detection ECCV 2020 DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion CVPR 2019 Regression Planning Networks NIPS 2019 Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks NIPS 2019 Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation CORL 2019 HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators CORL 2019 AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers CORL 2019 Learning to Navigate Using Mid-Level Visual Priors CORL 2019 TopNet: Structural Point Cloud Decoder CVPR 2019 Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks CVPR 2019 Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression CVPR 2019 SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints CVPR 2019 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks CVPR 2019 Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration CVPR 2019 Situational Fusion of Visual Representation for Visual Navigation ICCV 2019 3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera ICCV 2019 Taskonomy: Disentangling Task Transfer Learning IJCAI 2019 A Behavioral Approach to Visual Navigation with Graph Localization Networks RSS 2019 Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks CVPR 2018 Active Learning for Convolutional Neural Networks: A Core-Set Approach ICLR 2018 Demo2Vec: Reasoning Object Affordances From Online Videos CVPR 2018 Gibson Env: Real-World Perception for Embodied Agents CVPR 2018 CAR-Net: Clairvoyant Attentive Recurrent Network ECCV 2018 Adversarial Feature Augmentation for Unsupervised Domain Adaptation CVPR 2018 Translating Navigation Instructions in Natural Language to a High-Level Plan for Behavioral Robot Navigation EMNLP 2018 ROBOTURK: A Crowdsourcing Platform for Robotic Skill Learning through Imitation CORL 2018 Deep Learning Under Privileged Information Using Heteroscedastic Dropout CVPR 2018 Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision RSS 2018 Im2Pano3D: Extrapolating 360° Structure and Semantics Beyond the Field of View CVPR 2018 Taskonomy: Disentangling Task Transfer Learning CVPR 2018 SURREAL: Open-Source Reinforcement Learning Framework and Robot Manipulation Benchmark CORL 2018 Generalizing to Unseen Domains via Adversarial Data Augmentation NIPS 2018 Feedback Networks CVPR 2017 Tracking the Untrackable: Learning to Track Multiple Cues With Long-Term Dependencies ICCV 2017 Lattice Long Short-Term Memory for Human Action Recognition ICCV 2017 image2mass: Estimating the Mass of an Object from Its Image CORL 2017 Social Scene Understanding: End-To-End Multi-Person Action Localization and Collective Activity Recognition CVPR 2017 Deep View Morphing CVPR 2017 Learning Transferrable Representations for Unsupervised Domain Adaptation NIPS 2016 Structural-RNN: Deep Learning on Spatio-Temporal Graphs CVPR 2016 Deep Metric Learning via Lifted Structured Feature Embedding CVPR 2016 3D Semantic Parsing of Large-Scale Indoor Spaces CVPR 2016 Social LSTM: Human Trajectory Prediction in Crowded Spaces CVPR 2016 DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes CVPR 2016 A Probabilistic Framework for Real-time 3D Segmentation using Spatial, Temporal, and Semantic Cues RSS 2016 Universal Correspondence Network NIPS 2016 Data-Driven 3D Voxel Patterns for Object Category Recognition CVPR 2015 A Coarse-to-Fine Model for 3D Pose Estimation and Sub-Category Recognition CVPR 2015 Learning to Track: Online Multi-Object Tracking by Decision Making ICCV 2015 Action Recognition by Hierarchical Mid-Level Action Elements ICCV 2015 Unsupervised Semantic Parsing of Video Collections ICCV 2015 Watch-n-Patch: Unsupervised Understanding of Actions and Relations CVPR 2015 Enriching Object Detection With 2D-3D Registration and Continuous Viewpoint Estimation CVPR 2015 Combining 3D Shape, Color, and Motion for Robust Anytime Tracking RSS 2014 Structured Recurrent Temporal Restricted Boltzmann Machines ICML 2014 Learning an Image-based Motion Context for Multiple People Tracking CVPR 2014 Find the Best Path: An Efficient and Accurate Classifier for Image Hierarchies ICCV 2013 Understanding Indoor Scenes Using 3D Geometric Phrases CVPR 2013 3D Scene Understanding by Voxel-CRF ICCV 2013 Breaking the Chain: Liberation from the Temporal Markov Assumption for Tracking Human Poses ICCV 2013 Dense Object Reconstruction with Semantic Priors CVPR 2013 Accurate Localization of 3D Objects from RGB-D Data Using Segmentation Hypotheses CVPR 2013 Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines CVPR 2013 Efficient and Exact MAP-MRF Inference using Branch and Bound AISTATS 2012