OPERA: A Unified Omnimodal Progressive Spatio-Temporal Reasoning Agent for Referring Video Segmentation

arXiv:2609.33338 · cs.CV · Submitted 2026-09-27 · Read on arXiv

cs.CV

Submitted: 2026-09-27

Updated: 2026-09-27

Comments: 17 pages

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

Terminology

• Grounding — 51× in this paper · explained in 3 episodes
• Distillation — 47× in this paper · explained in 2 episodes
• GRPO — 40× in this paper · explained in 6 episodes
• Distillation Agent — 29× in this paper
• Temporal Reasoning — 18× in this paper · explained in 2 episodes
• Ablation — 13× in this paper · explained in 1 episode
• Benchmark — 13× in this paper · explained in 2 episodes
• Trace — 9× in this paper · explained in 2 episodes
• Transformer — 8× in this paper · explained in 2 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 5× in this paper
• Alignment — 4× in this paper · explained in 1 episode
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Semantic Alignment — 3× in this paper · explained in 3 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Quantization-Aware Training — 2× in this paper · explained in 3 episodes
• Query Complexity — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptation Score — 1× in this paper · explained in 1 episode
• Agent Harness — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multimodal Fusion — 1× in this paper · explained in 3 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Speculative Decoding — 1× in this paper · explained in 2 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• SimSD: Simple Speculative Decoding in Diffusion Language Models
• Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
• Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
• Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
• What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
• Cascaded Self-Evaluation Augmented Training for Lightweight Multimodal LLMs
• Natural-Language Agent Harnesses
• SAM 2: Segment Anything in Images and Videos
• Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
• DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration
• VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning
• MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration
• Qwen3-Omni Technical Report
• Qwen2.5-Omni Technical Report
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
• R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning
• ViLLa: Video Reasoning Segmentation with Large Language Model
• LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models