Search papers, labs, and topics across Lattice.
8
0
12
6
CalibForge reveals that adversarial calibration can dramatically enhance the effectiveness of training data for terminal agents, leading to unprecedented performance improvements on standard benchmarks.
FATE not only retains temporal information but also encodes synchronization in a reusable embedding space, outperforming existing models in both semantic and temporal tasks.
AVOC achieves a remarkable 4.9-point accuracy boost over the next best model in long-form audio-video comprehension, redefining efficiency in multimodal understanding.
Fine-tuning on DeNovoSWE catapults LLM performance in generating entire software repositories, achieving nearly an 8x improvement on a challenging benchmark.
Forget disjointed pipelines and structured inputs: PlanAudio uses an LLM and semantic latent chain-of-thought to directly synthesize unified audio from free-form text prompts.
LLMs can be sped up by over 2x without sacrificing accuracy, by compressing the input and predicting multiple output tokens at once using a unified framework.
Despite advances in AI, the best models struggle to match even a third of human performance in real-world video post-production tasks.
Autonomous ML research agents achieve significantly better long-horizon performance by maintaining durable state through a shared workspace, suggesting that orchestration and memory are more critical than raw reasoning power.
