Search papers, labs, and topics across Lattice.
Affiliation:
3
0
8
1
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.
Early backpropagation can boost training throughput by over 9% without sacrificing model performance.
Current AI systems struggle to conduct independent scientific research, with performance plummeting by nearly 50% when human guidance is removed.
