Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
7
0
9
1
An understanding-driven approach unlocks systematic spatial-memory management for world models, dramatically improving long-video generation quality.
Achieving state-of-the-art robust estimation efficiency, DiffSAC slashes hypothesis evaluations from over 10,000 to just dozens.
Robots can now learn new tasks on-the-fly without retraining, drastically cutting down the time and resources needed for adaptation.
Achieving a 3.25x speedup in prefill latency without sacrificing model performance could redefine efficiency benchmarks for omnimodal AI systems.
Light-Omni achieves a remarkable 12.1× speedup in video understanding while enhancing accuracy, redefining efficiency in agentic video processing.
EvoEmbedding outperforms leading embedding models by adapting its representations in real-time, revolutionizing long-context retrieval and agentic memory integration.
Forget static, single-turn personalization – PersonaVLM unlocks long-term, evolving user alignment in MLLMs, even surpassing GPT-4o.