#Research
Curated coverage on «Research»: releases, research, benchmarks, open-source.
OmniXRef: A Unified Framework for Video Editing with Multimodal References
Adobe Research has unveiled OmniXRef, a framework for video editing with multimodal references. It lets creators combine text, images, and video to control motion…
Stanford and Together AI Teach LLMs to Write Text Starting From an Outline: Generation Up to 31x Faster
Stanford and Together AI researchers brought VAR's "next-scale prediction" to text: the model writes an outline first, then fills in details. The claimed speedup is…
Apple and CMU Speed Up AI Agents 10x by Replacing Reasoning with Selection
Apple and Carnegie Mellon researchers propose dropping free-form "thinking" from ReAct agents and replacing it with a choice among options. The claimed speedup is…
CoworkEnv synthesizes training environments for AI coworkers: Qwen3-VL-8B jumps from 46.6 to 64.1
HKU's EgoWild2Dex Trains a Robot Hand on 538.9 Hours of "Messy" Video and One Hour on Hardware
RoboValue Tests Robot Action Evaluators on 35 Tasks and Finds Blind Spots
HoloBoxing teaches a humanoid to box in 7 minutes on a single GPU
Alibaba DAMO Releases RynnUnify: A 16B Model That Plans in Video and Drives a Robot
The 16B-parameter RynnUnify combines scene understanding, video generation and robot control: 51.5% success on 20 RoboCasa365 tasks and 46.7% on three real-world…
Easy-3Dfy builds a 3D scene from a single photo and outperforms SAM-3Dfy
Ziang Zhang's team split object generation from scene-layout estimation. Easy-3Dfy beat SAM-3Dfy on geometric metrics on Scene-Maker and 3D-FUTURE200.
OPST: A Model Fine-Tunes Itself on Its Own Questions, No Humans Required
New Algorithm Finds Nash Equilibrium in 5,600 Games to 1e-5 Precision
Hongbo Sun Proposes an Algorithm for Variational Inequalities: 6400 Problems, 1e-5
NX-AI's KronLSTM Changes the Delta Rule and Stabilizes Memory Without Normalization
TTR-Compressor Compresses Sequences with Regression and Cuts Visual Tokens by 55.6%
The new TTR-Compressor treats token compression as a regression problem and uses its coefficients as the compressed representation: same quality with 55.6% fewer…
ReGDiff Teaches Diffusion Models to Design Metamaterials Without Copying or Producing Defects
ReGDiff first organizes the latent space, then pushes the model away only from its nearest training samples during sampling. The resulting structures are novel and…