Search papers, labs, and topics across Lattice.
9
0
11
SPAR bridges the critical gap between semantic perception and pixel-level generation, achieving unprecedented quality in visual outputs without external supervision.
HELMSMAN slashes hardware costs by over 90% while enabling billion-scale index rebuilds in mere hours, revolutionizing ANNS for large-scale applications.
LLMs can actively reason across multiple videos at near state-of-the-art performance by iteratively dispatching specialized visual and audio agents, even when trained with a lightweight text-based simulator.
UniNote's two-stage training, combining contrastive SFT and RL, leapfrogs existing multimodal embeddings, delivering SOTA item-to-item retrieval performance with improved cost efficiency in real-world deployments.
LLMs can reason more efficiently by sharing intermediate thoughts during parallel search, achieving better accuracy with less computation.
Stop hand-engineering your multi-agent LLM systems: UnityMAS-O lets you train them end-to-end with RL, unlocking surprisingly large gains, especially for smaller models.
Stop relying on absolute LLM scores for RLHF: relative comparisons via tournaments yield significantly better rewards for long-form generation.
Current translation metrics miss the mark on capturing the cultural nuances and emotional resonance crucial for effective social media UGC translation.
Forget static graphs: TimeMM dynamically reweights user-item interactions based on recency and modality, adapting to evolving user preferences in multimodal recommendations.
