PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Images and Videos

arXiv:2608.24574 · cs.AI · Submitted 2026-08-25 · Read on arXiv

cs.AI

Submitted: 2026-08-25

Updated: 2026-08-25

Code: https://github.com/tusu-code/20260121-icml2026-2

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

Terminology

• Distillation — 39× in this paper · explained in 2 episodes
• Alignment — 26× in this paper · explained in 1 episode
• Grounding — 22× in this paper · explained in 3 episodes
• Consistency — 17× in this paper · explained in 3 episodes
• Benchmark — 11× in this paper · explained in 2 episodes
• Embeddings — 9× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Calibration — 6× in this paper · explained in 7 episodes
• Core — 5× in this paper · explained in 2 episodes
• Knowledge Distillation — 5× in this paper · explained in 11 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Transformer — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Transfer Learning — 2× in this paper · explained in 10 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Visual Instruction Tuning
• DINOv2: Learning Robust Visual Features without Supervision
• Distilling the Knowledge in a Neural Network
• The 2017 DAVIS Challenge on Video Object Segmentation
• Improved Neural Radiance Fields Using Pseudo-depth and Fusion
• VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
• FitNets: Hints for Thin Deep Nets
• Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
• Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
• PG-Video-LLaVA: Pixel Grounding Large Video-Language Models
• VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
• InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
• GLaMM: Pixel Grounding Large Multimodal Model
• OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
• F-LMM: Grounding Frozen Large Multimodal 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