arXiv||1 min read
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
Focuses on SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE.
Topic archive
Video AI news
Video generation, temporal reasoning, and media workflows. This page collects the latest briefings that match the topic so readers can follow one area without scanning the full feed.
Indexed briefings
151
Latest source-linked updates, ordered newest first.
Latest
Recent briefings
arXiv||1 min read
MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
Focuses on MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization.
arXiv||1 min read
MuSViT: A Foundation Vision Model for Sheet Music Representation
Focuses on MuSViT: A Foundation Vision Model for Sheet Music Representation.
arXiv||1 min read
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
Focuses on ABot-M0.5: Unified Mobility-and-Manipulation World Action Model.
arXiv||1 min read
From Black-Box to Clinical Insight: A Multi-Stage Explainable Framework for Speech-Based Cognitive Impairment Detection
Focuses on From Black-Box to Clinical Insight: A Multi-Stage Explainable Framework for Speech-Based Cognitive Impairment Detection.
arXiv||1 min read
MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations
Focuses on MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations.
arXiv||1 min read
DnA: Denoising Attention for Visual Tasks
Focuses on DnA: Denoising Attention for Visual Tasks.
arXiv||1 min read
PhysiFormer: Learning to Simulate Mechanics in World Space
Focuses on PhysiFormer: Learning to Simulate Mechanics in World Space.
arXiv||1 min read
HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models
Focuses on HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models.
arXiv||1 min read
RayPE: Ray-Space Positional Encoding for 3D-Aware Video Generation
Focuses on RayPE: Ray-Space Positional Encoding for 3D-Aware Video Generation.
arXiv||1 min read
See & Sniff: Learning Visuo-Olfactory Representations
Focuses on See & Sniff: Learning Visuo-Olfactory Representations.
arXiv||1 min read
EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting
Focuses on EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting.
arXiv||1 min read
Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect
Focuses on Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect.
arXiv||1 min read
VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks
Focuses on VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks.
arXiv||1 min read
Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models
Focuses on Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive Worl...
arXiv||1 min read
L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Models
Focuses on L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Models.
arXiv||1 min read
LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration
Focuses on LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration.
arXiv||1 min read
Scalable Operator Learning via Nyström Approximation With Denoising Applications
Focuses on Scalable Operator Learning via Nyström Approximation With Denoising Applications.
arXiv||1 min read
PHAST-Net: Attention-Guided, Physics-Informed Network for Unified Estimation of Ideal Time-Frequency Representations
Focuses on PHAST-Net: Attention-Guided, Physics-Informed Network for Unified Estimation of Ideal Time-Frequency Representations.
arXiv||1 min read
Vera: A Layered Diffusion Model for Content-Preserving Video Editing
Focuses on Vera: A Layered Diffusion Model for Content-Preserving Video Editing.
arXiv||1 min read
TuringViT: Making SOTA Vision Transformers Accessible to All
Focuses on TuringViT: Making SOTA Vision Transformers Accessible to All.
arXiv||1 min read
Geometry-Instructed Video Editing
Focuses on Geometry-Instructed Video Editing.
arXiv||1 min read
Tri-Efficient Transfer Learning for Point Cloud Videos
Focuses on Tri-Efficient Transfer Learning for Point Cloud Videos.
arXiv||1 min read
Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models
Focuses on Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models.
arXiv||1 min read
SteerVTE: Seamless Video Text Editing with Style and Glyph Control
Focuses on SteerVTE: Seamless Video Text Editing with Style and Glyph Control.
arXiv||1 min read
LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actions
Focuses on LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actions.
arXiv||1 min read
ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers
Focuses on ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers.
arXiv||1 min read
DataMagic: Transforming Tabular Data into Data Insight Video
Focuses on DataMagic: Transforming Tabular Data into Data Insight Video.
arXiv||1 min read
Gaussian Process Prior Variational Autoencoder for Endoscopic Videos
Focuses on Gaussian Process Prior Variational Autoencoder for Endoscopic Videos.
arXiv||1 min read
A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition
Focuses on A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition.
arXiv||1 min read
The Hidden Evolution of Disguised Visual Context inside the VLM
Focuses on The Hidden Evolution of Disguised Visual Context inside the VLM.
arXiv||1 min read
Triangular Consistency as a Universal Constraint for Learning Optical Flow
Focuses on Triangular Consistency as a Universal Constraint for Learning Optical Flow.
arXiv||1 min read
Gaussian Process Prior Variational Autoencoder for Endoscopic Videos
Focuses on Gaussian Process Prior Variational Autoencoder for Endoscopic Videos.
arXiv||1 min read
High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians
Focuses on High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians.
arXiv||1 min read
Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models
Focuses on Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models.
arXiv||1 min read
A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition
Focuses on A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition.