Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Peking University
6
4
8
9
Omni-modal foundation models achieve self-improvement via RL compute scaled to 1M context, leveraging asynchronous training and agentic grading for enhanced intelligence.
On-policy distillation is massively data-overfed: a single training prompt recovers most full-dataset performance gains, while just 16 prompts saturate 98.9% of reachable state space to match full-data distillation.
RailSyn achieves up to 4.9 points improvement in RFOD detection accuracy by intelligently generating synthetic data that addresses specific task deficiencies.
RailGen reduces the object pixel area by up to 58x, enabling a leap in detection accuracy for small-scale foreign objects in railway safety applications.
1.58-bit LLMs are surprisingly more resilient to sparsity than their full-precision counterparts, opening new avenues for extreme compression.
LLMs trained with a novel "second-order rollout" that generates critiques in addition to responses learn more effectively from the same data, unlocking better reasoning.