Tag: AI language models
Browse our exclusive articles!
LongCoT Benchmark: Advancing Long-Horizon Chain-of-Thought AI
Discover LongCoT, a benchmark with 2,500 expert problems to test and improve long-horizon chain-of-thought reasoning in AI models.
How to Synthesize High-Quality Pretraining Data Effectively
Discover key strategies for synthesizing high-quality pretraining data, including prompt design, generator models, and source data selection.
Peer-Predictive Self-Training Boosts Language Model Reasoning
Discover how Peer-Predictive Self-Training improves language model reasoning accuracy without external supervision using collaborative learning.
Boost LLM Performance with Multilingual Post-Training
Explore how multilingual post-training improves large language models, enhancing low-resource languages and cross-lingual transfer beyond English-only trai...
KV Packet: Efficient KV Caching for Faster LLM Inference
Discover KV Packet, a recomputation-free KV caching method that boosts Large Language Model performance by reducing latency and maintaining accuracy.