Search papers, labs, and topics across Lattice.
7
0
11
0
Evolved harnesses encode a shared abstract playbook that adapts to language-specific challenges, revealing a nuanced interplay between model limitations and engineering demands.
Iterative image retrieval can now adapt contextually, achieving a 44.1 R@1 on multi-turn searches—far surpassing previous benchmarks.
Achieving 19 times lower inference latency than diffusion models, UniGen-AR redefines the efficiency of unified visual generation.
A single generalist model outperforms specialized systems, achieving over 35% improvement in real-world robotic task success.
Retrieving the right prompts can boost LMM performance by up to 30%, challenging the assumption that similarity guarantees effectiveness in in-context learning.
Forget sparse sampling – this VLM digests 2x-4x more video frames by compressing each down to a single token.
LLMs can scalably annotate motion capture data to produce semantically rich descriptions of bimanual interactions, enabling higher-quality generation of dexterous hand motions.
