Search papers, labs, and topics across Lattice.
3
0
6
5
Emotion-oriented MLLMs can now achieve unprecedented accuracy in visual emotional intelligence, revealing critical insights into their limitations and capabilities.
OKR achieves a remarkable +6.5% mAP improvement over existing methods by preventing knowledge interference in domain-incremental object detection.
LALMs can now dynamically re-listen to audio during reasoning, leading to state-of-the-art performance on complex audio comprehension tasks.
