Search papers, labs, and topics across Lattice.
7
0
9
15
Achieving softmax-level expressiveness with a fraction of the latency, SANA-Video 2.0 redefines efficiency in high-resolution video generation.
Jet-Long achieves up to 1.39x throughput improvements while maintaining accuracy across long-context tasks, setting a new standard for zero-shot context extension in LLMs.
LongLive-RAG transforms long video generation by enabling the use of a searchable memory of past latents, drastically reducing error accumulation.
Cosmos 3 sets a new benchmark for omnimodal models, outperforming existing state-of-the-art in both Text-to-Image and Image-to-Video tasks.
Real-time, high-resolution video editing is now possible on a single consumer GPU, thanks to a novel hybrid diffusion transformer and system-level optimizations that achieve 24 FPS at 1280x704.
Grounding boosts spatial reasoning in VLMs: explicitly linking language to 2D and 3D scene elements lets models decompose complex spatial problems and improve performance even on non-grounded tasks.
By structuring diffusion-based driving models around a "scaffold" of frozen structural tokens, Fast-dDrive achieves a 12x speedup over autoregressive baselines while improving trajectory accuracy.
