Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
7
0
10
10
Spatial intelligence tasks are solved 5.6x faster with zero accuracy loss by reframing them as classification problems, eliminating autoregressive decoding entirely.
A single MLLM can now perform temporal grounding and video QA with significant inference speedups by treating them as structured decision tasks.
A unified proactive generation framework enables LLMs to form reusable factual memories from streaming video without compromising real-time perception.
Most current robotic manipulation policies fail to retain crucial historical information, leading to significant performance drops in partially observable tasks, but a novel memory framework boosts success rates across diverse challenges.
VideoChat3 achieves unprecedented generalization in video understanding while maintaining high efficiency, outperforming larger models with just 4 billion parameters.