Search papers, labs, and topics across Lattice.
3
0
3
Frontier generalist systems have effectively mastered high-level visual semantics and spatial reasoning, yet they still stubbornly fail to displace dedicated models on metric geometry, dense temporal tracking, and fine-grained visual fidelity.
Achieving a staggering 79x reduction in decoding latency, Parallel Tube Decoding redefines efficiency in spatio-temporal video grounding.
Expensive end-to-end omni pre-training degrades foundational reasoning and vision, yet simply routing timestamped ASR transcripts into a frozen VLM matches or beats native omni architectures across 56 benchmarks.
