Systems
Every system (architecture) the survey reviewed, with its memory representation, how memory is stored and retrieved, and what can change during deployment. Combine filters to find systems that work like yours.
297 of 297 systems
- 3D-Mem 3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
- 3DLLM-Mem 3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
- ABot-AgentOS ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory
- ActionEngine ActionEngine: From Reactive to Programmatic GUI Agents via State Machine Memory
- AdaMM Beyond Retrieval: Analytic Memory for Multimodal Agents
- Adaptive Workflow Agents Adaptive Multimodal Agents-Based Framework for Automatic Workflow Execution
- AesopAgent AesopAgent: Agent-driven Evolutionary System on Story-to-Video Production
- Affordance RAG Affordance RAG: Hierarchical Multimodal Retrieval With Affordance-Aware Embodied Memory for Mobile Manipulation
- Agent S Agent S: An Open Agentic Framework that Uses Computers Like a Human
- AgentCVR AgentCVR: Active Multi-Agent Cross-Video Reasoning via Script-Simulated Reinforcement Learning
- Agentic ASR Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation
- AgentOCR AgentOCR: Optical Context Compression for Long-Horizon Multimodal Agents
- AGMem Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents
- Analytic Concept-Centric Memory Analytic Concept-Centric Memory for Agentic Embodied Manipulation
- Anim-Director Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation
- AniME AniME: Adaptive Multi-Agent Planning for Long Animation Generation
- AnomalyAgent AnomalyAgent: Agentic Multimodal Reasoning for Few-Shot Anomaly Detection
- AppAgent AppAgent: Multimodal Agents as Smartphone Users
- AppAgent v2 AppAgent v2: Advanced Agent for Flexible Mobile Interactions
- AtlasVA AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents
- ATMem What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States
- AUGUSTUS AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory
- Auto-scaling Continuous Memory Auto-scaling Continuous Memory for GUI Agent
- AutoDroid AutoDroid: LLM-powered Task Automation in Android
- AutoMMemo Learning to Learn from Multimodal Experience
- AViLA AViLA: Asynchronous Vision-Language Agent for Streaming Multimodal Data Interaction
- BehaviorVLA From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model
- BrainNav Endowing Embodied Agents with Spatial Reasoning Capabilities for Vision-and-Language Navigation
- BundleSDF BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
- BundleTrack BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
- C-Nav C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
- camroll-agent Personal AI Agent for Camera Roll VQA
- CANVAS CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding
- CAUSALNAV CausalNav: A Long-term Embodied Navigation System for Autonomous Mobile Robots in Dynamic Outdoor Scenarios
- Chain-of-Memory Chain-of-Memory: Enhancing GUI Agents for Cross-Application Navigation
- CMA Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing
- CMMR-VLN CMMR-VLN: Vision-and-Language Navigation via Continual Multimodal Memory Retrieval
- Co-Director Co-Director: Agentic Generative Video Storytelling
- CogniVerse CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning
- ComfyClaw ComfyClaw: Self-Evolving Skill Harnesses for Image Generation Workflows
- ConceptGraphs ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning
- Context-as-Memory Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval
- Continual Harness Continual Harness: Online Adaptation for Self-Improving Foundation Agents
- CuriosAI CASTLE CuriosAI Submission to the CASTLE Challenge at EgoVis 2026
- Darwinian Memory Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution
- Deep Video Discovery Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
- DeepImageSearch DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories
- DeLTa DeLTa: Demonstration and Language-Guided Novel Transparent Object Manipulation
- DGSG-Mind DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding
- DigimonGPT DigimonGPT: An Evolvable Agent with Hierarchical Human-like Memory for Video Question Answering
- DovSG Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation
- DRAE DRAE: Dynamic Retrieval-Augmented Expert Networks for Lifelong Learning and Task Adaptation in Robotics
- Dream to Recall / Memoir Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation
- DreamFactory DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework
- DreamRunner DreamRunner: Fine-Grained Compositional Story-to-Video Generation with Retrieval-Augmented Motion Adaptation
- DriveWAM Selective KV Memory DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
- Dynam3D Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
- DynaMem DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation
- EAM Executable Agentic Memory for GUI Agent
- ECHO ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models
- Echo-MC Experience Transfer for Multimodal LLM Agents in Minecraft Game
- EchoVLA EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation
- EGAgent Agentic Very Long Video Understanding
- EgoButler EgoLife: Towards Egocentric Life Assistant
- EgoMAS MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
- EgoMem EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Models
- Ella Ella: Embodied Social Agents with Lifelong Memory
- Embodied VideoAgent Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding
- Embodied-RAG Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation
- Embodied-SlotSSM Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective
- EmbodiedLGR-Agent EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic Agents
- EmbodiedRAG EmbodiedRAG: Dynamic 3D Scene Graph Retrieval for Efficient and Scalable Robot Task Planning
- EmbodiSkill EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
- eMEM eMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agents
- EMKG EMKG: Embodied Memory Knowledge Graphs for Object-Goal Navigation in Dynamic Open Worlds
- Episodic Memory Verbalization Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience
- EventMemAgent EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use
- Evo-MedAgent Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve
- EvolvingAgent EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks
- EvoVid EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
- FilmAgent FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces
- FinAcumen (Financial Memory + Financial Tools harness) FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness
- FinAgent A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist
- FinSight (Code Agent with Variable Memory) FinSight: Towards Real-World Financial Deep Research
- Flash-VStream Flash-VStream: Efficient Real-Time Understanding for Long Video Streams
- FlexMem Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism
- FOLIO FOLIO: Focused Semantic Memory for Streaming Video Understanding
- Frames2LoRA Frames2LoRA: Parametric Video Internalization for Vision-Language Models
- GA-VLN GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation
- GCAgent GCAgent: Graph-Centric Episodic Memory for Long Video Agents
- GEM-Occ GEM-Occ: From Visual Geometry Evidence to Embodied Semantic Occupancy Memory
- GEMS GEMS: Agent-Native Multimodal Generation with Memory and Skills
- GenEvolve GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
- GeoEvolver Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observers
- GeoForge GeoForge: Non-Parametric Self-Evolving Agents for Earth-Observation Reasoning
- GEST Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios
- GraphEQA GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering
- GraphPad GraphPad: Inference-Time 3D Scene Graph Updates for Embodied Question Answering
- GraphPilot GraphPilot: GUI Task Automation with One-Step LLM Reasoning Powered by Knowledge Graph
- GRGA (Graph-based Retrieval-Generation Agent) Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding
- GUI-explorer GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent
- H2-EMV Learning to Forget -- Hierarchical Episodic Memory for Lifelong Robot Deployment
- HAM-VLN HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation
- HD-EPIC Long-Video Reasoning Semantic and Visual Evidence for Efficient Long-Video Reasoning: A Solution for the HD-EPIC VQA Challenge
- HiKEY HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering
- HiMe HiMe: Hierarchical Embodied Memory for Long-Horizon Vision-Language-Action Control
- HIMM HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering
- HippoMM HippoMM: Hippocampal-inspired Multimodal Memory for Long Audiovisual Event Understanding
- HyLoVQA HyLoVQA: Dynamic Hypernetwork-Generated Low-Rank Adaptation for Continual Visual Question Answering
- HyMEM Hybrid Self-evolving Structured Memory for GUI Agents
- IMPACT-CYCLE IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory
- KARMA KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
- KnowAct-GUIClaw KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
- Kubrick Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation
- L2-VMAS Dual Latent Memory for Visual Multi-agent System
- LaMem-VLA Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
- Latent Spatial Memory Latent Spatial Memory for Video World Models
- Light-Omni Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory
- LiteWebAgent LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications
- LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics
- LongVideoAgent LongVideoAgent: Multi-Agent Reasoning with Long Videos
- LUMA-RAG LUMA-RAG: Lifelong Multimodal Agents with Provably Stable Streaming Alignment
- M2A M2A: Multimodal Memory Agent with Dual-Layer Hybrid Memory for Long-Term Personalized Interactions
- M3-Agent Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
- MA-LMM MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
- MAGNET MAGNET: Towards Adaptive GUI Agents with Memory-Driven Knowledge Evolution
- MangaFlow MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation
- MAP-VLA MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation
- MARDoc MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA
- MARS MARS: Technical Report for the CASTLE Challenge at EgoVis 2026
- MAViS MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling
- MEM MEM: Multi-Scale Embodied Memory for Vision Language Action Models
- Mem-W Mem-W: Latent Memory-Native GUI Agents
- MemCtrl MemCtrl: Using MLLMs as Active Memory Controllers on Embodied Agents
- MemEIC MemEIC: A Step Toward Continual and Compositional Knowledge Editing
- MeMento Long-Horizon Embodied Decision-Making via Multimodal Memory Compression
- MEMENTO Personalization Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization
- MementoGUI MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
- MemLearner MemLearner: Learning to Query Context memory for Video World Models
- MemOCR MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
- MemoPhishAgent MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection
- MEMORA MEMORA: Embodied Action Memory from Egocentric Videos for Reasoning and Planning
- Memorize-and-Generate Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation
- Memory-Augmented Object Captioning Agent Memory-Augmented Vision-Language Agents for Persistent and Semantically Consistent Object Captioning
- MemoryExplorer / LMEE-Bench Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration
- MemoryVLA MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
- MemoryVLA++ MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models
- MemShot Memory Shot for Long-Term Dialogue
- MemSlides MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision
- MemVerse MemVerse: Multimodal Memory for Lifelong Learning Agents
- MGA MGA: Memory-Driven GUI Agent for Observation-Centric Interaction
- MindForge MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
- Mirage-1 Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills
- MIRIX MIRIX: Multi-Agent Memory System for LLM-Based Agents
- MM-Mem From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
- MMA MMA: Multimodal Memory Agent
- MMed-RAG MMed-RAG: Versatile Multimodal RAG System for Medical Vision-Language Models
- Mobile-Agent-E Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks
- Mobile-Agent-V Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation
- Mobile-Agent-v2 Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
- MobileGPT MobileGPT: Augmenting LLM with Human-like App Memory for Mobile Task Automation
- MobileUse MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation
- MobiMem Beyond Training: Enabling Self-Evolution of Agents with MobiMem
- MoMa-LLM Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation
- MoMuSE MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues
- MovieAgent Automated Movie Generation via Multi-Agent CoT Planning
- MovieChat MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
- MovieChat+ MovieChat+: Question-aware Sparse Memory for Long Video Question Answering
- MovieDreamer MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence
- MSGNav MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation
- MTU3D Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
- MuKV MuKV: Multi-Granular Key-Value Cache for Efficient Long Video Understanding
- Multimodal Spatial Language Maps Multimodal spatial language maps for robot navigation and manipulation
- MUSE MUSE: Agentic 3D Scene Authoring via Memory-Grounded Incremental Requirement Satisfaction
- MuSEAgent MuSEAgent: Multimodal Semantic Experience Agent
- NeSy-Spatial Self-Evolving Neuro-Symbolic Skills for Tool-Augmented Spatial Reasoning
- NS-Mem Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory
- O-MARC O-MARC: Omni Memory-Augmented Compression Distillation for Efficient Video Understanding
- ObsGraph ObsGraph: Hierarchical Observation Representation for Embodied Reasoning and Exploration
- ObsMem WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents
- OCR-Memory OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory
- OdysseyAgent GUI Odyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices
- OmAgent OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer
- Omni-SimpleMem Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
- One Sentence One Drama One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems
- Open Scene Graphs Open Scene Graphs for Open World Object-Goal Navigation
- Open-World 3D Scene Graph RAG Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning
- Optimus-1 Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
- OptimusVLA Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation
- PAL-UI PAL-UI: Planning with Active Look-back for Vision-Based GUI Agents
- PathNavigate PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA
- PEAM PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft
- Pensieve Memory-QA: Answering Recall Questions Based on Multimodal Memories
- Persode Persode: Personalized Visual Journaling with Episodic Memory-Aware AI Agent
- PersonaVLM PersonaVLM: Long-Term Personalized Multimodal LLMs
- PhotoFlow PhotoFlow: Agentic 3D Virtual Photography Missions
- PixelRAG PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation
- Planning from Imagination Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language Navigation
- PlanRAG-Audio PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding
- PMMC PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agents
- POLAR Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions
- PolarMem PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models
- PRISM Scaling Short-Term Memory of Visuomotor Policies for Long-Horizon Tasks
- Ptah Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation
- PyraVid PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning
- Reflective Dialogue VQA Reflective Dialogue between Teacher and Solver Agents for Video Question Answering
- ReflectWorld-MM ReflectWorld-MM: An Entity-Oriented Multi-Media Memory System for Open-Ended Video Streams
- ReKV Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
- ReMA (Recursive Multimodal Agent) Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline
- ReMEmbR ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation
- RenderMem RenderMem: Rendering as Spatial Memory Retrieval
- REVEAL REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation Detection
- REVEAL (Retrieval-Augmented Visual-Language Pre-Training) REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory
- ReWind ReWind: Understanding Long Videos with Instructed Learnable Memory
- RGB-Only Reconstruction and MPC RGB-Only Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control
- Robo-Cortex Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction
- RoboEXP RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation
- RoboMemory RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems
- RoboOS-NeXT RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration
- ROVER ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning
- RRM RRM: Experience-Driven Reflective Retrieval Memory for Long-Horizon Multimodal Reasoning
- S3Mem S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering
- SAVEMem Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
- Scene Graph Memory Modeling Dynamic Environments with Scene Graph Memory
- SceneGraphGrounder SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching
- ScrapMem ScrapMem: Multimodal Scrapbook Memory for Long-Horizon Agents
- ScriptViz The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation
- SE-GA SE-GA: Memory-Augmented Self-Evolution for GUI Agents
- Sensorimotor Primitives Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations
- SkeMex Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
- Skill-3D Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning
- SKILL.nb SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows
- SkillGraph SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology
- SkillMimicGen SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment
- SOMA Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action
- SpaceMind SpaceMind: A Modular and Self-Evolving Embodied Vision-Language Agent Framework for Autonomous On-orbit Servicing
- SpatialGPT SpatialGPT: Zero-Shot Vision-and-Language Navigation via Spatial CoT over Structured Spatial Memory
- STAMP STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual Environments
- Stateful Streaming ASR (State Carry-over / State Rollback) Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents
- StoryAgent StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration
- StoryMem StoryMem: Multi-shot Long Video Storytelling with Memory
- StreamChat Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
- StreamFlow StreamFlow: Dynamic Memory Flows for Streaming Video Understanding
- StreamMeCo StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
- StreamMind StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding
- SymbOmni SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learning
- TAME TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistant
- TARIC TARIC: Memory-Augmented Traversability-Aware Outdoor VLN under Interrupted Semantic Cues
- Task-driven Perception and Manipulation Task-Driven Perception and Manipulation for Constrained Placement of Unknown Objects
- TaskMem Task-Focused Memorization for Multimodal Agents
- TeleMem TeleMem: Building Long-Term and Multimodal Memory for Agentic AI
- TGL Proactive Trigger and Routing Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?
- ToolMerge Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval
- Train the Agent Not the Expert Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning
- TRAM TRAM: Enhancing Multimodal Reasoning with Trajectory-Derived Auxiliary Memory
- TRM-VLA TRM-VLA: Temporal-Aware Chain-of-Thought Reasoning and Memorization for Vision-Language-Action Models
- UI-KOBE UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents
- UI-Mem UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents
- UI-TARS UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- UI-Voyager UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
- UniversalRAG UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities
- UniWM Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight
- V-Mem V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memory
- Vesta Vesta: A Generalist Embodied Reasoning Model
- Vgent Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
- Video-EM Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding
- video-SALMONN S video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
- VideoAgent VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding
- VideoARM VideoARM: Adaptive Reasoning and Memory for Long Video Understanding
- VideoAuteur VideoAuteur: Towards Long Narrative Video Generation
- VideoDirectorGPT VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning
- VideoGen-of-Thought VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention
- VideoLLaMB VideoLLaMB: Long Video Understanding with Recurrent Memory Bridges
- VideoLucy VideoLucy: Deep Memory Backtracking for Long Video Understanding
- VideoStreaming Streaming Long Video Understanding with Large Language Models
- VideoStudio VideoStudio: Generating Consistent-Content and Multi-Scene Videos
- VideoTree VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
- VIGA Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
- ViLoMem ViLoMem: Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
- VimRAG VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
- Vision to Geometry / 3DSPMR Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration
- VisMem VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
- VISOR VISOR: Visual Evidence Space for Robust GUI and Visual Agent Reasoning
- VisRAG VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
- VISTA VISTA: A Visual Harness for Reasoning in an Interactive World
- Visual Memory QA Visual Memory QA: Your Personal Photo and Video Search Agent
- VisualClaw VisualClaw: A Real-Time, Personalized Agent for the Physical World
- VisualMem Personal Visual Memory from Explicit and Implicit Evidence
- VLA-Pro VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
- VLM-MSGraph VLM-MSGraph: Vision Language Model-enabled Multi-hierarchical Scene Graph for robotic assembly
- Vlogger Vlogger: Make Your Dream A Vlog
- VoiceMem VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction
- Voyager Voyager: An Open-Ended Embodied Agent with Large Language Models
- Where Did I Leave My Glasses? Where Did I Leave My Glasses? Open-Vocabulary Semantic Exploration in Real-World Semi-Static Environments
- WnW (Waxing-and-Waning KV Cache) WnW: Waxing-and-Waning KV Cache for Long-Form Speech LLMs
- WorldMM WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
- YODO (You Only Demonstrate Once) You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration