ParaThinker trains LLMs for native parallel reasoning and reports 7 to 12 percent higher accuracy on math benchmarks over sequential thinking with modest latency overhead.
Magicdec: Breaking the latency-throughput tradeoff for long context generation with speculative decoding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
ParaThinker trains LLMs for native parallel reasoning and reports 7 to 12 percent higher accuracy on math benchmarks over sequential thinking with modest latency overhead.