-
EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion
score 4
关键词(1): coding；顶会接收: ECCV
-
MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration
score 4
关键词(3): scaling, lightweight, vision-language；顶会接收: ECCV
-
SynCLIP: Synonym-Coherent Language-Image Pretraining for Robust Open-Vocabulary Dense Perception
score 4
关键词(1): pretraining；顶会接收: CVPR
-
NVAITC AI Scientist: A Governed End-to-End Research System -- A Hypertension GWAS Case Study
score 4
机构: NVIDIA；关键词(3): deployment, agentic, code generation
-
DynEval: Holistic Evaluations of T2I Generative Models in the Wild
score 4
关键词(4): fine-tuning, reasoning, vision-language, text-to-image；顶会接收: ECCV
-
Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
score 4
关键词(2): retrieval-augmented, reasoning；顶会接收: ECCV
-
Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory
score 4
关键词(1): reasoning；顶会接收: CVPR
-
Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO
score 4
关键词(1): fine-tuning；顶会接收: ECCV
-
FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry
score 4
关键词(2): scaling, lightweight；顶会接收: ECCV
-
NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception
score 4
机构: MIT；关键词(1): real-time
-
Controlling Motion Transfer in Diffusion Transformers via Attention Heads
score 3
顶会接收: ECCV
-
SVI360: Spherical Video Interpolation
score 3
顶会接收: ECCV
-
MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
score 3
机构: Apple
-
Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency
score 3
顶会接收: ECCV