Latest
- AutoMetrics: Approximate Human Judgments with Automatically Generated Evaluators
- Contextualized Privacy Defense for LLM Agents
- Real-Time Reasoning Agents in Evolving Environments
- Searching for Privacy Risks in LLM Agents via Simulation
- Attacking Vision-Language Computer Agents via Pop-ups
- Distilling an End-to-End Voice Assistant Without Instruction Training Data
- EgoNormia: Benchmarking Physical Social Norm Understanding
- SWE-smith: Scaling Data for Software Engineering Agents
- Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering
- Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping
- Auditing Gender Presentation Differences in Text-to-Image Models
- Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization
- LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
- Continual Sequence Generation with Adaptive Compositional Modules
- Robustness of Demonstration-based Learning Under Limited Data Scenario
- Continual Learning for Text Classification with Information Disentanglement Based Regularization