Search papers, labs, and topics across Lattice.
8
0
11
0
LPM restores user-generated videos with such high fidelity that it accounts for 45% of Kuaishou's total viewing time while slashing bandwidth costs by 20%.
Spectral analysis reveals that tokens with dynamic cross-layer evolution are crucial for preserving semantic integrity, leading to more efficient MLLMs.
MLLMs excel at precision but falter dramatically in extracting complete product specifications from multiple images, with a mere 49.9% recovery rate.
MemVenom reveals that web agents can be compromised with up to 99.15% success through sophisticated memory poisoning attacks that bypass traditional defenses.
Get high-fidelity tactile simulations with 65% speedup and 40% less memory by combining coarse physics with neural implicit reconstruction.
Current image restoration models still fail to strike the right balance between noise reduction, detail fidelity, and accurate color in real-world, low-light portrait scenarios, highlighting a critical gap this challenge aims to close.
Current Chinese AI-generated text detection benchmarks are too homogeneous; C-ReD fixes this with real-world prompts and diverse LLMs, enabling better generalization.
By optimizing gradient inversions across hierarchical GAN feature spaces, GIFD achieves pixel-perfect reconstructions of private data in federated learning, even in challenging out-of-distribution scenarios.
