Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
6 papers published across 1 lab.
Open-weight diffusion models can now render complex, bilingual text and control intricate layouts with near-perfect accuracy, closing a critical gap with proprietary systems.
Frontier generalist computer-use agents, previously closed-source, are now open for systematic study and community development, with the first release achieving significant performance gains.
Frontier models can be used sparingly for long-horizon tasks by a weak agent that learns to predict when it needs help, then keeps the strong model on a leash.
Open multimodal code intelligence models now rival proprietary systems, driven by a novel rubric-based data synthesis pipeline that precisely evaluates program correctness, code quality, and visual output.
A single open-source model now performs multi-character scene dubbing, in-filling edits, and multi-turn revisions with natural language direction, all at 271 fps.
Open-weight diffusion models can now render complex, bilingual text and control intricate layouts with near-perfect accuracy, closing a critical gap with proprietary systems.
Frontier generalist computer-use agents, previously closed-source, are now open for systematic study and community development, with the first release achieving significant performance gains.
Frontier models can be used sparingly for long-horizon tasks by a weak agent that learns to predict when it needs help, then keeps the strong model on a leash.
Open multimodal code intelligence models now rival proprietary systems, driven by a novel rubric-based data synthesis pipeline that precisely evaluates program correctness, code quality, and visual output.
A single open-source model now performs multi-character scene dubbing, in-filling edits, and multi-turn revisions with natural language direction, all at 271 fps.
A 2.5B Tamil-first LLM achieves state-of-the-art translation and native language understanding, while demonstrating functional tool-calling, offering a blueprint for under-represented language AI development.