Search papers, labs, and topics across Lattice.
4
0
5
5
DARTree achieves a staggering 9.73脳 speedup in autoregressive decoding while accepting nearly 99% more tokens per round than existing methods.
AutoDesign outperforms existing design systems by aligning with human design principles and achieving superior poster generation quality through recursive self-improvement.
A simple training framework boosts pixel-level tampering detection performance in VLMs by over 26%, showcasing the power of balanced sampling and late-injection strategies.
LLMs can be surprisingly effective vision models, even without full fine-tuning, thanks to inherent foundational properties in specific layers that transfer via a simple "random label bridge training" technique.
