Researchers Propose 'Sleep' Mechanism to Fix LLM Context Limits
A new consolidation technique lets language models compress long conversations into persistent memory, solving a critical scaling bottleneck.
A new consolidation technique lets language models compress long conversations into persistent memory, solving a critical scaling bottleneck.
Researchers propose entity-focused approach to keep multimodal models accurate across different video datasets.
Researchers develop a technique to compress powerful video generators into faster versions that work with incomplete information.
Researchers demonstrate that selectively repeating transformer layers in masked diffusion models cuts training costs by 70% while improving reasoning capabilities.

Researchers tackle a fundamental tradeoff in subject-driven synthesis by leveraging multimodal language models alongside specialized identity conditioning.

Researchers combine distillation and reinforcement learning to create faster text-to-image models that align better with human preferences.
New framework handles transparent materials and complex topology shifts that have stymied previous video-to-4D systems.
Researchers release Prism, a modular toolkit designed to streamline continuous learning in vision-language systems without requiring code rewrites.
New research argues that scaling AI agents depends as much on system design as foundation model improvements.