Search papers, labs, and topics across Lattice.
13 papers from Meta AI (FAIR) on Natural Language Processing
Agentic Business Process Management offers a blueprint for aligning AI agents with organizational goals, moving beyond simple automation to a framework of constrained autonomy.
LLMs can now infer plausible stage layouts from unstructured text alone, opening up new possibilities for automated media production.
OmniSONAR halves cross-lingual search error on FLORES and reduces error by 15x on BIBLE, proving that truly universal sentence embeddings across thousands of languages and modalities are now within reach.
Forget scaling laws: a specialized 8B parameter translation model can outperform a 70B general-purpose LLM on 1,600 languages.
LLMs struggle to generate diverse and specific connections between concepts, even with high token budgets and "thinking" prompts, revealing a gap in creative associative reasoning.
Forget imbalanced LoRA usage: ReMix leverages reinforcement learning to route effectively among LoRAs, boosting performance in parameter-efficient fine-tuning.
Uncover hidden patient subgroups with distinct treatment responses using a new Bayesian clustering approach that goes beyond traditional unsupervised methods.
Pre-normalization in Transformers is the culprit behind the mysterious link between massive activation outliers and attention sinks, but decoupling them reveals their distinct functions: global parameterization vs. local attention modulation.
Unlocking the secrets of viral video ads: a new MLLM framework reveals which initial moments hook viewers and drive conversions.
By explicitly disentangling target features with MLLM guidance, MeGU achieves superior unlearning performance without sacrificing model utility, outperforming existing methods that struggle with the inherent entanglement of semantic concepts in model representations.
Despite growing interest, queer NLP research remains largely reactive, highlighting biases instead of building proactive solutions, leaving significant opportunities for stakeholder-driven and intersectional approaches.
Finally, a streaming ASR model matches Whisper's offline transcription quality while maintaining sub-second latency.
Ditch the pre-trained models: PAST directly learns speech tokens from phonetic data, outperforming existing methods in representation and reconstruction.
