ECCV 2024 accepted papers on Multi-agent systems and games
20 of the 2,387 papers accepted at ECCV 2024 (0.8%) are on Multi-agent systems and games, compared with 0.7% at ECCV 2022. They fall into 2 topics.
See ECCV 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Human-AI and goal-conditioned · 17 papers
- See and Think: Embodied Agent in Virtual Environment (43 citations)
- MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction (40 citations)
- VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions (40 citations)
- V-IRL: Grounding Virtual Intelligence in Real Life (31 citations)
- Solving Motion Planning Tasks with a Scalable Generative Model (27 citations)
- SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic (24 citations)
- Hetecooper: Feature Collaboration Graph for Heterogeneous Collaborative Perception (14 citations)
- IFTR: An Instance-Level Fusion Transformer for Visual Collaborative Perception (12 citations)
- ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments (9 citations)
- Plug and Play: A Representation Enhanced Domain Adapter for Collaborative Perception (8 citations)
- Situated Instruction Following (8 citations)
- Frontier-enhanced Topological Memory with Improved Exploration Awareness for Embodied Visual Navigation (7 citations)
and 5 more in the interactive map.
LLM agents · 3 papers
- OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web (93 citations)
- Improving Agent Behaviors with RL Fine-tuning for Autonomous Driving (14 citations)
- R^2-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations (3 citations)
