LatentMem is a new memory system that helps teams of AI agents remember the right things for their specific jobs without overloading them with text.
This paper teaches AI how to fix broken Lean math proofs by learning from the compiler’s feedback, not just from finished, perfect proofs.
SLIME is a new way to train chatbots so they follow human preferences without forgetting how to write well.
The paper shows that three popular ways to control language models—fine-tuning a few weights, LoRA, and activation steering—are actually the same kind of action: a dynamic weight update driven by a control knob.
Multi-agent LLM systems often use LoRA adapters so each agent has a special role, but they all rebuild almost the same KV cache, wasting memory and time.
This paper shows a simple, one-model way to dub videos that makes the new voice and the lips move together naturally.
Diffusion models make pictures from noise but often miss what people actually want in the prompt or what looks good to humans.
The paper asks which small, add-on training tricks (PEFT) work best when we teach language models with yes/no rewards we can check (RLVR).
DreamOmni3 lets people edit and create images by combining text, example images, and quick hand-drawn scribbles.
IC-Effect is a new way to add special effects to existing videos by following a text instruction while keeping everything else unchanged.
Recursive transformers save memory by reusing the same layer over and over, but that makes them less expressive and hurts accuracy.
MetaCanvas lets a multimodal language model (MLLM) sketch a plan inside the generator’s hidden canvas so diffusion models can follow it patch by patch.