Search papers, labs, and topics across Lattice.
Affiliation:
7
0
10
Auditing demographic bias across guidance scales no longer requires brute-force image generation: causal abstraction enables a lightweight transformer to predict fairness shifts across the entire CFG spectrum.
Fine-grained MoE designs can outperform dense vision encoders while dramatically reducing latency, challenging the status quo in image and video understanding.
ViCo3D achieves a groundbreaking 1.8x improvement in collaborative 3D object detection performance by merging LiDAR data with advanced visual representations from vision foundation models.
Context-gated latent-action conditioning enables VLA models to achieve unprecedented success rates in robot manipulation tasks without relying on separate action-generation modules.
Dynamic gating allows DGSeg to filter out noise and ambiguity in segmentation cues, leading to superior performance in reasoning segmentation tasks.
Editing software through feature manipulation can enhance usability and efficiency, achieving a 42.6% boost in modification accuracy over traditional LLM approaches.
