Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
5
0
8
4
Most multimodal models fail to truly understand tool use in real-world egocentric videos, with even Gemini-3.1-Pro struggling to ground actions in visual evidence.
Rubric-based scoring reveals that vision-language models can significantly improve their grounding in visual evidence, enhancing reasoning and instruction adherence.
AURORA-LM achieves state-of-the-art performance in language generation by leveraging a continuous-latent diffusion framework that preserves text fidelity while enhancing generative capabilities.
Forget dialogue summaries – FileGram builds user profiles directly from atomic file-system actions, unlocking a richer, more privacy-preserving approach to agent personalization.
Turns out, just showing a vision-language model the last few frames of a video stream beats fancy architectures designed for long-term memory.