Search papers, labs, and topics across Lattice.
9
0
8
4
Closed-loop learning in embodied agents can lead to a staggering 11.1x speedup in inference while achieving record performance on complex tasks.
Leading MLLMs falter on the new VideoGAIA benchmark, scoring under 60% accuracy in complex, multi-turn video understanding tasks.
A physics-guided approach in VeinCast reveals that integrating structured atmospheric relations can significantly enhance the accuracy of medium-range weather forecasts.
Existing models miss critical visual evidence in metaphor understanding, but M$^3$R-Reasoner closes the gap, outperforming larger models in both accuracy and justification metrics.
PEC boosts the fidelity of virtual contrast-enhanced breast MRIs by effectively recalibrating intensity scales, outperforming conventional methods in critical evaluation metrics.
Hierarchical tokenization transforms bounding-box representation, leading to substantial improvements in localization accuracy and model performance across various benchmarks.
Hallucinations in LLM-generated news summaries can be effectively mitigated using a novel Chain-of-Thought reasoning framework, leading to more accurate and reliable timeline summarization.
Surpassing existing methods, Orchestra-o1 achieves a 10.3% accuracy improvement on the OmniGAIA benchmark by enabling seamless collaboration across multiple modalities.
Struct-Searcher achieves a remarkable 17.2% accuracy boost in multimodal information seeking by effectively managing conflicting evidence through a dynamic structural graph.
