Search papers, labs, and topics across Lattice.
8
0
11
Current video generation benchmarks overlook crucial aspects of physical plausibility and temporal coherence, highlighting the need for holistic evaluation metrics like PhyScore.
LLMs can generate syntactically valid software architectures from requirements, but their struggle with relational reasoning leads to structurally unsound designs.
Real-time, open-ended video understanding is now possible: AURA enables VideoLLMs to proactively respond to live video streams, moving beyond simple captioning.
LLMs struggle with code comprehension, but a simple RNN pass over their embeddings can boost accuracy by over 5%.
LLMs struggle with low-resource general-purpose programming languages, and surprisingly, translating code *to* a low-resource language is harder than generating it from text.
LLMs in collaborative coding often stumble on interaction subtleties, leading to a new class of problems called "Interaction Smells" that can now be systematically identified and mitigated.
Forget tweaking knobs – this new Gram-matrix-based audio representation lets you *retrieve* the perfect, editable audio effect preset, outperforming standard methods.
By explicitly modeling emotion co-occurrence patterns, MPCL achieves state-of-the-art performance in mixed emotion recognition, outperforming existing methods that neglect the structured correlations among coexisting emotions.
