Yuchen Wu

Autonomous vehicles can now better handle degraded sensor data in adverse conditions thanks to a new unsupervised domain adaptation method that leverages both LiDAR and RGB data.

Forget hand-designed agent communication topologies: Agent Q-Mix learns decentralized communication strategies that boost accuracy and token efficiency in LLM multi-agent systems.

SFT on interleaved plot-solution data *hurts* geometric reasoning in MLLMs, but a novel RL framework called Faire flips the script to achieve state-of-the-art performance by enforcing causal constraints.

Visual reasoning gets a boost: forcing models to "draft" their reasoning in code and render visual proofs dramatically improves performance by bridging the gap between perception and logical structure.