Search papers, labs, and topics across Lattice.
OPPO AI Center
7
0
11
Parent-Conditioned Drafting can boost LLM inference speed by up to 29.5% while increasing the effective acceptance length of generated outputs.
MMLDSum-LLM outperforms existing models by significantly enhancing key information coverage and cross-modal consistency in long-document summarization.
TimeThink revolutionizes video reasoning by enabling models to pinpoint relevant temporal evidence with unprecedented accuracy, outperforming existing approaches.
ProMSA achieves superior accuracy in KB-VQA by dynamically selecting retrieval strategies, outperforming traditional fixed pipelines.
Gradient explosions in token-level distillation are tamed by a novel normalization technique, leading to robust improvements in multimodal reasoning tasks.
MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.
VLMs can achieve up to 4.2x faster inference by simply skipping redundant pixels before they even enter the Vision Transformer.
