Search papers, labs, and topics across Lattice.
Tsinghua University, Shanghai AI Laboratory
7
0
11
4
A unified proactive generation framework enables LLMs to form reusable factual memories from streaming video without compromising real-time perception.
Self-Routing adapts optimization strategies on-the-fly, leading to significant improvements in mathematical reasoning tasks without relying on external supervision.
HarnessEval-W transforms world model evaluation from mere scoring to a transparent reasoning process that mirrors human judgment.
QUMem revolutionizes user-state inference by enabling LLMs to retrieve contextually relevant memories that evolve over time, outperforming existing methods on key benchmarks.
Query-conditioned reuse boosts agent success by 10.7 points while slashing token usage by nearly 50%, transforming how we leverage past experiences in AI tasks.
WDL-OPD boosts MATH500 accuracy from 0.630 to 0.685, showcasing a powerful new approach to stabilizing on-policy distillation.
Streaming spatial intelligence remains a significant hurdle for multimodal LLMs, with top models trailing human experts by 27 points in allocentric mapping tasks.
