ExpSeek helps web-browsing AI agents ask for help exactly when they feel unsure, instead of stuffing them with tips at the very beginning.
MoCha is a new AI that swaps a person in a video with a new character using only one mask on one frame and a few reference photos.
Group-based reinforcement learning for reasoning (like GRPO) uses the group's average reward as a baseline, but that makes its 'advantage' estimates biased.
JudgeRLVR teaches a model to be a strict judge of answers before it learns to generate them, which trims bad ideas early.
This paper introduces YaPO, a way to gently nudge a language model’s hidden thoughts so it behaves better without retraining it.
RubricHub is a huge (about 110,000) collection of detailed grading guides (rubrics) for many kinds of questions like health, science, writing, and chat.
UM-Text is a single AI that understands both your words and your picture to add or change text in images so it looks like it truly belongs there.
This paper shows how to make powerful image‑generating Transformers run fast on phones without needing the cloud.
The paper builds a new way to create realistic, long conversations between people and AI that use tools like databases.
MemoBrain is like a helpful co-pilot for AI that keeps important thoughts neat and ready so the main thinker (the agent) doesn’t get overwhelmed.
Transformers are powerful but slow because regular self-attention compares every token with every other token, which grows too fast for long sequences.
Large Vision-Language Models (LVLMs) look great on single images but often stumble when they must reason across multiple images.