Trending Research
Emerging Properties in Unified Multimodal Pretraining
Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems.
Ranked #2 on
Image Editing
on ImgEdit-Data
MNN: A Universal and Efficient Inference Engine
alibaba/MNN
•
•
Deploying deep learning models on mobile devices draws more and more attention recently.
DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing
Our evaluation on four different unstructured document analysis tasks demonstrates that DocETL finds plans with outputs that are 25 to 80% more accurate than well-engineered baselines, addressing a critical gap in unstructured data analysis.
Logits-Based Finetuning
dvlab-research/logits-based-finetuning
•
•
We deeply explore the main contributors of OOD detection and find that reconstruction-based pretext tasks have the potential to provide a generally applicable and efficacious prior, which benefits the model in learning intrinsic data distributions of the ID dataset.
Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
To address this challenge, we introduce the first benchmark and metric suite for poster generation, which pairs recent conference papers with author-designed posters and evaluates outputs on (i)Visual Quality-semantic alignment with human posters, (ii)Textual Coherence-language fluency, (iii)Holistic Assessment-six fine-grained aesthetic and informational criteria scored by a VLM-as-judge, and notably (iv)PaperQuiz-the poster's ability to convey core paper content as measured by VLMs answering generated quizzes.
DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
Large Vision-Language Models (VLMs) have shown strong capabilities in multimodal understanding and reasoning, yet they are primarily constrained by text-based reasoning processes.
MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning
Class-Incremental Learning (CIL) requires models to continually acquire knowledge of new classes without forgetting old ones.
Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders
We address the problem of gaze target estimation, which aims to predict where a person is looking in a scene.
Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments
We present Orbit, a unified and modular framework for robot learning powered by NVIDIA Isaac Sim.
Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
The G\"odel machine proposed a theoretical alternative: a self-improving AI that repeatedly modifies itself in a provably beneficial manner.
