Silvio Savarese

Salesforce (United States) — United States

Engineering · Physical Sciences

94h-index41.4kcitations517works2.52yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Robotics and Sensor-Based Localization(94), Human Pose and Action Recognition(90), Multimodal Machine Learning Applications(75), Advanced Image and Video Retrieval Techniques(71), Advanced Vision and Imaging(68)

Publications517 total

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
arXiv (Cornell University)·2025Open Access
LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
arXiv (Cornell University)·2025Open Access
SSR: Socratic Self-Refine for Large Language Model Reasoning
arXiv (Cornell University)·2025Open Access
Moirai 2.0: When Less Is More for Time Series Forecasting
arXiv (Cornell University)·2025Open Access
Test-Time Adaptation for LLM Agents via Environment Interaction
ArXiv.org·2025Open Access
Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics
arXiv (Cornell University)·2025Open Access
BLIP3o-NEXT: Next Frontier of Native Image Generation
arXiv (Cornell University)·2025Open Access
ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning
arXiv (Cornell University)·2025Open Access
xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
arXiv (Cornell University)·2025Open Access
WALT: Web Agents that Learn Tools
arXiv (Cornell University)·2025Open Access
CoDA: Coding LM via Diffusion Adaptation
arXiv (Cornell University)·2025Open Access
UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
arXiv (Cornell University)·2025Open Access
SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents
arXiv (Cornell University)·2025Open Access
Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data
arXiv (Cornell University)·2025Open Access
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
arXiv (Cornell University)·2025Open Access
CoAct-1: Computer-using Multi-Agent System with Coding Actions
ArXiv.org·2025Open Access
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models
arXiv (Cornell University)·2025Open Access
Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models
arXiv (Cornell University)·2025Open Access
GTA1: GUI Test-time Scaling Agent
arXiv (Cornell University)·2025Open Access
page 1 of 26Next →

Frequent Co-authors

Wongun Choi(7), Ozan Şener(6), Xiang Yu(6), Alexandre Alahi(5), Li Fei-Fei(4), Amir Sadeghian(4), Mani Golparvar‐Fard(4), Feniosky Peña‐Mora(4), Leonidas Guibas(3), Amir Zamir(3), Christopher Choy(3), JunYoung Gwak(3), Roberto Martín-Martín(3), Ian Reid(3), Alexandre Robicquet(2), Anne Lynn S. Chang(2), Thomas Funkhouser(2), Pat Hanrahan(2), Qixing Huang(2), Zimo Li(2)