Search papers, labs, and topics across Lattice.
Affiliation:
5
0
9
Benchmark Radar is presented, a living database and search engine for retrieval and discovery of AI benchmarks, covering LLM evaluation, agentic and tool-use benchmarks, coding, reasoning, safety, and domain-specific evaluations.
The 9B WeMM-Embedding variant sets a new benchmark in multimodal embeddings, outperforming larger models while being deployed at scale across WeChat's diverse applications.
Semantic Affine Consistency transforms how visual tokenizers align latent semantics, resulting in a 26% reduction in gFID and setting a new benchmark for diffusion models.
Geo-Embed achieves a 15.3% performance boost over existing models, redefining how we approach multimodal urban understanding.
Automating vehicle braking controller design via offline RL could eliminate extensive manual calibration, a major bottleneck in the automotive industry.
