Papers

Filtered to self-supervised learning · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

PhiZero: A World Model Built Around Physical Language

158 upvotes · 30 JUL 2026 · Shuyao Shang, Yuqi Wang, Ruopeng Gao et al.

This paper introduces PhiZero, a world model that uses physical language to predict how the physical world evolves, allowing for more explicit reasoning and potentially more realistic simulations. Practitioners might care because this approach could lead to more realistic and interactive world modeling in applications like robotics, video games, and virtual reality.

physical world modelsself-supervised learningreason-then-render paradigmworld dynamicsphysical language

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

69 upvotes · 26 JUL 2026 · Qinsi Wang, Jing Shi, Huazheng Wang et al.

This paper introduces a new method to improve large language models (LLMs) called RLSVR, which uses a task-transformation technique to generate self-verifiable rewards, enabling LLM self-improvement on open-ended tasks. Practitioners might care about this because it could lead to more reliable and scalable self-improvement methods for LLMs.

reinforcement learninglarge language modelstask transformationverifiable rewardsself-supervised learning

Self-Supervised Learning of Structured Dynamics from Videos

18 upvotes · 23 JUL 2026 · Lukas Knobel, Andrew Zisserman, Yuki M. Asano

This paper learns how to separate the motion in videos into two parts: the camera's movement and the objects' movements, allowing for more accurate and meaningful analysis of the video content. Practitioners might care because this can improve the performance of computer vision models on tasks like object tracking and motion analysis.

video representation learningstructured dynamicsself-supervised learningvision transformersmotion analysis