Search papers, labs, and topics across Lattice.
7
0
11
1
Coding agents are failing to meet user requests, with a mere 31.5% success rate, highlighting a critical gap in requirement recovery that must be addressed.
Long-tailed point cloud dataset distillation can boost classification accuracy by 7 points, challenging the limits of existing methods.
Current LLMs struggle with multi-granularity event analysis, revealing critical performance gaps that could hinder their application in complex narrative tasks.
Unifying velocity and endpoint predictions reveals a method that significantly boosts generative model performance without major architectural changes.
Forget parallel corpora: CodePivot shows you can train a 7B model to beat behemoth LLMs at multilingual code transpilation by pivoting through Python and using a clever RL reward.
Autonomous driving policies that ace open-loop tests can still crash and burn in the real world, because they learn to ignore the reactive nature of closed-loop environments.
LLMs can now generate Verilog code that's not just correct, but also optimized for real-world hardware constraints like power, performance, and area, thanks to a novel multi-agent system with evolving memory.
