Search papers, labs, and topics across Lattice.
6
0
8
0
AI-guided simulations reveal the precise mechanisms of siloxane poisoning in gas sensors, paving the way for designing sensors that resist degradation.
Today's best video models achieve near-zero success rates on interactive video generation, revealing a stark gap in multimodal reasoning and physical grounding.
By explicitly disentangling and fusing spatial textures with frequency-based structural features, FEDSNet achieves state-of-the-art few-shot fine-grained classification, demonstrating that frequency information is crucial for overcoming texture biases and improving robustness.
Forget real-world video datasets: training VLMs on just 7.7K synthetic videos with temporal primitives beats 165K real-world examples, unlocking surprisingly effective transfer learning for video reasoning.
Multimodal LLMs get a serious reasoning boost from Durian, a difficulty-aware normalization that tames the instability caused by extreme samples and noisy rewards.
Current video benchmarks are too simple; UniVBench offers the first unified framework to measure the integrated capabilities of video foundation models using complex, multi-shot videos and a standardized evaluation system.
