OmniFysics-Nano-V2 Technical Report: Understanding the Physical World Across Modalities

arXiv:2609.25738 · cs.AI · Submitted 2026-09-22 · Read on arXiv

cs.AI

Submitted: 2026-09-22

Updated: 2026-09-22

Comments: 24 pages

Code: https://github.com/Fysics-AI/OmniFysics-Nano-V2

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 40× in this paper · explained in 2 episodes
• Alignment — 18× in this paper · explained in 1 episode
• GRPO — 12× in this paper · explained in 6 episodes
• Reinforcement Learning — 10× in this paper · explained in 4 episodes
• Embeddings — 7× in this paper · explained in 2 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Accuracy — 4× in this paper · explained in 1 episode
• Vision-language models — 4× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Transformer — 3× in this paper · explained in 2 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• In International Conference on Learning Representations — 2× in this paper
• Temporal Reasoning — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Calibration — 1× in this paper · explained in 7 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Full-duplex interaction — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Parameter Efficiency — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Verifiability — 1× in this paper · explained in 2 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
• Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Physion: Evaluating Physical Prediction from Vision in Humans and Machines
• Can Vision Language Models Learn Intuitive Physics from Interaction?
• PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
• MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
• CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
• Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
• Gemini: A Family of Highly Capable Multimodal Models
• AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?
• OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization
• FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoning
• LLaVA-OneVision: Easy Visual Task Transfer
• Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
• QuantiPhy: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models
• Baichuan-Omni-1.5 Technical Report
• OmniBench: Towards The Future of Universal Omni-Language Models
• Reward Design for Physical Reasoning in Vision-Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection