Search papers, labs, and topics across Lattice.
6
0
10
0
Constraining rollout updates to complementary subspaces can enhance performance and stability in large language models, achieving up to 27.69 points improvement over existing methods.
GUI-Lens boosts GUI grounding accuracy by nearly 25% by enabling iterative visual refinement, transforming how VLMs interact with complex interfaces.
TC-UAP is the first method to effectively safeguard videos from both reference- and tuning-based customization, achieving unprecedented identity protection.
Untangling multilayer networks just got easier: T-GINEE uses tensors to explicitly model cross-layer dependencies, outperforming methods that treat layers independently.
Stop relying on LLMs to "hallucinate" reasoning paths – SEARCH-R uses a fine-tuned Llama3.1-8B model and dependency tree-based retrieval to navigate multi-hop question answering more reliably.
Forget independent feature extraction: a new architecture uses LVLMs to explicitly model the relationships between drone and satellite imagery, substantially boosting geolocalization accuracy.
