paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago

HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration

Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs. However, existing monocular 4D reconstruction methods primarily focus on isolated objects, often failing under the severe occlusions and complex dynamics inherent in multi-object interactions. To bridge this gap, we propose HAT-4D, the first agentic framework designed to reconstruct the 3D geometry, temporal dynamics, and physical interactions of multiple objects from a single video. By integrating VLMs with a multi-le

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “HAT-4D: Lifting Monocular Video for 4D Multi-Object Interact” ≈ “AgentCore-8B””
LinkedLinked via unknownInto the Omniverse: Three Workflows for Improving Vision AI Agent Accuracy With Synthetic Data and Fine-Tuning →
FuzzySimilar title/name (fuzzy) · 87%zhayujie/CowAgent →
“Fuzzy title match (0.94): “HAT-4D: Lifting Monocular Video for 4D Multi-Object Interact” ≈ “zhayujie/CowAgent””
FuzzySimilar title/name (fuzzy) · 66%open-multi-agent/open-multi-agent →
“Fuzzy title match (0.78): “HAT-4D: Lifting Monocular Video for 4D Multi-Object Interact” ≈ “open-multi-agent/open-multi-agent””
FuzzySimilar title/name (fuzzy) · 59%NousResearch/hermes-agent →
“Fuzzy title match (0.73): “HAT-4D: Lifting Monocular Video for 4D Multi-Object Interact” ≈ “NousResearch/hermes-agent””
FuzzySimilar title/name (fuzzy) · 59%2FastLabs/agent-squad →
“Fuzzy title match (0.73): “HAT-4D: Lifting Monocular Video for 4D Multi-Object Interact” ≈ “2FastLabs/agent-squad””
FuzzySimilar title/name (fuzzy) · 59%Developer-Y/cs-video-courses →
“Fuzzy title match (0.73): “HAT-4D: Lifting Monocular Video for 4D Multi-Object Interact” ≈ “Developer-Y/cs-video-courses””
FuzzySimilar title/name (fuzzy) · 87%SWE-agent/SWE-agent →
“Fuzzy title match (0.94): “HAT-4D: Lifting Monocular Video for 4D Multi-Object Interact” ≈ “SWE-agent/SWE-agent””

Has model

modelAgentCore-8B

Covers (incoming)

newsInto the Omniverse: Three Workflows for Improving Vision AI Agent Accuracy With Synthetic Data and Fine-Tuning

Implements (incoming)

repozhayujie/CowAgent repoopen-multi-agent/open-multi-agent repoNousResearch/hermes-agent repo2FastLabs/agent-squad repoDeveloper-Y/cs-video-courses repoSWE-agent/SWE-agent repoiflytek/astron-agent repobojieli/ai-agent-book

Related across the graph

repoSWE-agent/SWE-agent repoDeveloper-Y/cs-video-courses newsInto the Omniverse: Three Workflows for Improving Vision AI Agent Accuracy With Synthetic Data and Fine-Tuning repoopen-multi-agent/open-multi-agent repozhayujie/CowAgent repoNousResearch/hermes-agent repobojieli/ai-agent-book modelAgentCore-8B repo2FastLabs/agent-squad repoiflytek/astron-agent

Topics

cs.AI