Silvio Savarese

papers

2,431

total citations

papers (18)

Unified Training of Universal Time Series Forecasting Transformers

ICML 2024arXiv

428

citations

CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

NEURIPS 2022arXiv

395

citations

ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding

CVPR 2023arXiv

307

citations

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

NEURIPS 2023arXiv

202

citations

APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

NEURIPS 2025arXiv

citations

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

ICML 2025arXiv

citations

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

ICML 2025arXiv

citations

TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild

ICCV 2021arXiv

citations

JRDB-Act: A Large-Scale Dataset for Spatio-Temporal Action, Social Group and Activity Detection

CVPR 2022arXiv

citations

Procedure-Aware Pretraining for Instructional Video Understanding

CVPR 2023arXiv

citations

Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents

ICLR 2025arXiv

citations

DyMU: Dynamic Merging and Virtual Unmerging for Efficient Variable-Length VLMs

NEURIPS 2025

citations

X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-modal Reasoning

ECCV 2024

citations

Text2Data: Low-Resource Data Generation with Textual Control

AAAI 2025arXiv

citations

Silvio Savarese

papers (18)

Unified Training of Universal Time Series Forecasting Transformers

CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding

HIVE: Harnessing Human Feedback for Instructional Visual Editing

Topological Planning With Transformers for Vision-and-Language Navigation

Generative Sparse Detection Networks for 3D Single-shot Object Detection

APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild

JRDB-Act: A Large-Scale Dataset for Spatio-Temporal Action, Social Group and Activity Detection

Procedure-Aware Pretraining for Instructional Video Understanding

Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents

DyMU: Dynamic Merging and Virtual Unmerging for Efficient Variable-Length VLMs

X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-modal Reasoning

Text2Data: Low-Resource Data Generation with Textual Control

papers (18)

Unified Training of Universal Time Series Forecasting Transformers

CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding

HIVE: Harnessing Human Feedback for Instructional Visual Editing

Topological Planning With Transformers for Vision-and-Language Navigation

Generative Sparse Detection Networks for 3D Single-shot Object Detection

APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild

JRDB-Act: A Large-Scale Dataset for Spatio-Temporal Action, Social Group and Activity Detection

Procedure-Aware Pretraining for Instructional Video Understanding

Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents

DyMU: Dynamic Merging and Virtual Unmerging for Efficient Variable-Length VLMs

X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-modal Reasoning

Text2Data: Low-Resource Data Generation with Textual Control