arXiv||1 min read
EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
Focuses on EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation.
Topic archive
Vision AI news
Perception, multimodal systems, 3D, and visual generation. This page collects the latest briefings that match the topic so readers can follow one area without scanning the full feed.
Indexed briefings
1059
Latest source-linked updates, ordered newest first.
Latest
Recent briefings
arXiv||1 min read
DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution
Focuses on DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution.
arXiv||1 min read
Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization
Focuses on Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization.
arXiv||1 min read
Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence
Focuses on Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence.
arXiv||1 min read
EdiTikZ: Scientific Figure Editing from Revision Trajectories
Focuses on EdiTikZ: Scientific Figure Editing from Revision Trajectories.
arXiv||1 min read
Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching
Focuses on Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching.
arXiv||1 min read
InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations
Focuses on InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations.
arXiv||1 min read
Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videos
Focuses on Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videos.
arXiv||1 min read
MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents
Focuses on MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents.
arXiv||1 min read
Language-Informed Flow Matching for Trend-Guided Structure-Based 3D Molecular Generation
Focuses on Language-Informed Flow Matching for Trend-Guided Structure-Based 3D Molecular Generation.
arXiv||1 min read
From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents
Focuses on From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents.
arXiv||1 min read
Agentic Multimodal Models for Environmental Hyperspectral Unmixing
Focuses on Agentic Multimodal Models for Environmental Hyperspectral Unmixing.
arXiv||1 min read
Soft Posterior Speaker Injection for Multi-Talker Speech Recognition
Focuses on Soft Posterior Speaker Injection for Multi-Talker Speech Recognition.
arXiv||1 min read
LOCI: A Locator-Critic with Refinement Loop
Focuses on LOCI: A Locator-Critic with Refinement Loop.
arXiv||1 min read
TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models
Focuses on TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models.
arXiv||1 min read
Audio-Driven Adversarial Defense for 3D Talking Face Generation with totally Visual Fidelity Preservation
Focuses on Audio-Driven Adversarial Defense for 3D Talking Face Generation with totally Visual Fidelity Preservation.
arXiv||1 min read
RetailAgent: Structured Adverse Timing in Self-Conditioned Multimodal LLM Trading Agents
Focuses on RetailAgent: Structured Adverse Timing in Self-Conditioned Multimodal LLM Trading Agents.
arXiv||1 min read
STEGNav: Spatio-Temporal Event Graph Reasoning for Multimodal Lifelong Object Navigation
Focuses on STEGNav: Spatio-Temporal Event Graph Reasoning for Multimodal Lifelong Object Navigation.
arXiv||1 min read
TAMI: Temporally Aligned, Missingness-Aware, and Interpretable Multimodal Fusion for Mental Health Assessment in Older Adults with Mild Cognitive Impairment
Focuses on TAMI: Temporally Aligned, Missingness-Aware, and Interpretable Multimodal Fusion for Mental Health Assessment in Older Adults with Mild Cognitive Impairment.
arXiv||1 min read
MuSP-Bench: Advanced Multimodal Benchmarking of Music Understanding across Score and Performance
Focuses on MuSP-Bench: Advanced Multimodal Benchmarking of Music Understanding across Score and Performance.
arXiv||1 min read
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
Focuses on UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City.
arXiv||1 min read
CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators
Focuses on CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators.
arXiv||1 min read
Embodied Scene Rearrangement Planning
Focuses on Embodied Scene Rearrangement Planning.
arXiv||1 min read
WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents
Focuses on WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents.
arXiv||1 min read
PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Plans
Focuses on PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Plans.
arXiv||1 min read
Decoupled I/O-Dominant Pipelines for Large-Scale Whole-Slide Image Embedding Extraction
Focuses on Decoupled I/O-Dominant Pipelines for Large-Scale Whole-Slide Image Embedding Extraction.
arXiv||1 min read
Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems
Focuses on Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems.
arXiv||1 min read
VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following
Focuses on VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following.
arXiv||1 min read
VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction
Focuses on VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction.
arXiv||1 min read
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
Focuses on LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training.
arXiv||1 min read
TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding
Focuses on TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding.
arXiv||1 min read
Code World Model: Coding Agent as World Brain
Focuses on Code World Model: Coding Agent as World Brain.
arXiv||1 min read
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
Focuses on StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing.
arXiv||1 min read
Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models
Focuses on Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models.
arXiv||1 min read
How AI Experiences Art: Emergent Aesthetic Structure in a Self-Supervised Multimodal Embedding Space
Focuses on How AI Experiences Art: Emergent Aesthetic Structure in a Self-Supervised Multimodal Embedding Space.
arXiv||1 min read
Omni-Interactive Universal Embedder
Focuses on Omni-Interactive Universal Embedder.