Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture DiscoveryGoogle DeepMind · arXiv (Cornell University)Mar 7Self-Supervised Multi-Modal World Model with 4D Space-Time EmbeddingAllen Institute for AI · arXiv (Cornell University)Mar 7VisualDeltas: Learning Preferences from Visual Quality PerturbationsAlibaba · arXiv (Cornell University)Mar 7Do generative video models understand physical principles?Google DeepMind · IEEE Winter Conference on Applications of Computer Vision19 citationsMar 6Autoregressive Styled Text Image Generation, but Make it ReliableAlphabet · IEEE Winter Conference on Applications of Computer Vision5 citationsMar 6Modeling and Learning Multiple Hypotheses for Monocular 3D Object DetectionMicrosoft · IEEE Winter Conference on Applications of Computer Vision1 citationMar 6DICE: Discrete Inversion Enabling Controllable Editing for Masked Generative ModelsGoogle DeepMind · IEEE Winter Conference on Applications of Computer Vision1 citationMar 6Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistanceMeta · IEEE Winter Conference on Applications of Computer Vision1 citationMar 6Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive AlignmentNVIDIA · IEEE Winter Conference on Applications of Computer Vision1 citationMar 6VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language ModelsNVIDIA · IEEE Winter Conference on Applications of Computer Vision1 citationMar 6Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image SynthesisNVIDIA · IEEE Winter Conference on Applications of Computer Vision1 citationMar 6Conditional Text-to-Image Generation with Reference GuidanceMicrosoft · IEEE Winter Conference on Applications of Computer Vision1 citationMar 6X-JEPA: A Novel Joint Learning Cross-Modal Predictive Alignment Framework for Remote Sensing Image RetrievalGoogle DeepMind · IEEE Winter Conference on Applications of Computer VisionMar 6Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality HallucinationsGoogle DeepMind · IEEE Winter Conference on Applications of Computer VisionMar 6SmoothDiffusion-VE: Real-time Generative Video Editing Using Adaptive Feature CacheNVIDIA · IEEE Winter Conference on Applications of Computer VisionMar 6Pyramidal Spectrum: Frequency-based Hierarchically Vector Quantized VAE for VideosAlphabet · IEEE Winter Conference on Applications of Computer VisionMar 6FairScene: Learning Class-Disentangled 2D/3D Representations for Semantic Scene CompletionMicrosoft · IEEE Winter Conference on Applications of Computer VisionMar 6Safe Vision-Language Models via Unsafe Weights ManipulationNVIDIA · IEEE Winter Conference on Applications of Computer VisionMar 6Reconstructing Realistic and Relightable EyesMeta · IEEE Winter Conference on Applications of Computer VisionMar 6BrightRate: Quality Assessment for User-Generated HDR VideosAlphabet · IEEE Winter Conference on Applications of Computer VisionMar 6Data-Driven Loss Functions for Inference-Time Optimization in Text-to-ImageNVIDIA · IEEE Winter Conference on Applications of Computer VisionMar 6Mitigating Backdoor Attacks via Trigger Reconstruction and Model HardeningMicrosoft · IEEE Winter Conference on Applications of Computer VisionMar 6TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal AnchorsNVIDIA · IEEE Winter Conference on Applications of Computer VisionMar 6Segmentation-Aware Latent Diffusion for Satellite Image Super-Resolution: Enabling Smallholder Farm Boundary DelineationAlphabet, Google DeepMind · IEEE Winter Conference on Applications of Computer VisionMar 6Deep Learning-Enhanced Cloud Accounting Model for Real-Time Fraud and Financial Risk PredictionMeta · Innovations in Machine, Engineering, and Digital Conference (IMED)Mar 6