Search papers, labs, and topics across Lattice.
5
0
9
1
Current facial expression editing models can't simultaneously preserve identity and accurately manipulate expressions, revealing a critical need for better fine-grained instruction following.
Polarization cues, often overlooked, can significantly boost camouflaged object detection by explicitly guiding RGB feature learning, leading to state-of-the-art performance.
Current robot manipulation benchmarks fail to capture the messy reality of real-world deployment, so this work introduces a new benchmark, ManipArena, to close the sim2real gap.
Agentic coding models can achieve near-SOTA performance by specializing in distinct coding domains before unifying them via on-policy distillation.
Robot swarms can now handle complex, synchronized tasks in uncertain environments without getting stuck, thanks to a new planning method that dynamically adapts to risk and prevents deadlocks.
