Search papers, labs, and topics across Lattice.
Affiliation:
5
0
9
3
This work proposes RetireOPD (Self-Retiring On-Policy Distillation), which first optimizes a decoupled, skill-conditioned teacher with environment rewards and then trains a skill-free student jointly with RL and OPD.
Standard translation metrics and 235B-parameter LLM judges actively reward the worst social media translations due to cultural blindness, but progressively decaying masked cultural scaffolding enables an 8B model to rival Gemini-3.1-Pro.
SpatialGuard transforms 3D spatial text-to-image generation from a mere prompt-following exercise into a verifiable planning and validation process, significantly enhancing spatial accuracy.
Fixed exponents in neural scaling laws reveal that optimizing coefficients could unlock significant performance gains in large language models.
LLMs can learn to recognize when they lack sufficient information for reasoning and proactively ask for clarification, leading to more reliable and concise answers.
