Search papers, labs, and topics across Lattice.
Nanjing University
5
0
6
3
Teacher-forcing-free EEG2Text decoding is not only feasible but also significantly enhances model evaluation, challenging previous assumptions about EEG's linguistic capabilities.
Roadwork zones can confuse VLMs, but WorkDrive's causal reasoning framework cuts trajectory prediction errors by up to 12% in these challenging environments.
SearchEyes achieves state-of-the-art performance in multimodal search by unifying training data, environments, and rewards into a cohesive simulated world.
Latent reasoning can beat explicit Chain-of-Thought – but only if you force it to learn causal dynamics via a visual world model, not just language.
Current image editing models, even closed-source ones, still fall short on complex and creative instruction-based tasks, as revealed by a new interpretable QA-based evaluation framework.
