Search papers, labs, and topics across Lattice.
Zhejiang University
4
0
6
3
Filtering out noise from reasoning traces can drastically improve hallucination detection in large reasoning models, leading to more reliable AI outputs.
Ghosting artifacts in HDR imaging are dramatically reduced by an adaptive, agent-driven framework that learns from past experiences and scene dynamics.
Streaming reasoning steps can boost multi-agent system performance by 7.3 percentage points on average, revealing a new dimension for scaling effectiveness and efficiency.
Language models are increasingly doing their real work in the "invisible" latent space, not the tokens we see.
