Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Probing and Leveraging Video Diffusion Transformer Features for Robust Point TrackingGoogle DeepMind · arXiv (Cornell University)8 citationsDec 23, 2025QuarkAudio Technical ReportAlibaba · arXiv (Cornell University)4 citationsDec 23, 2025Generalization of RLVR Using Causal Reasoning as a TestbedMicrosoft · arXiv (Cornell University)3 citationsDec 23, 2025M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented GenerationNVIDIA · arXiv (Cornell University)3 citationsDec 23, 2025SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation ModelsTechnology Innovation Institute · arXiv (Cornell University)3 citationsDec 23, 2025Two-phase collaborative model compression training for joint pruning and quantizationiFlytek · Neural Networks3 citationsDec 23, 2025UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View SynthesisAlphabet · arXiv (Cornell University)2 citationsDec 23, 2025Improving ML Training Data with Gold-Standard Quality MetricsAlphabet · arXiv (Cornell University)2 citationsDec 23, 2025RAG-Guardrails Integration for AI Content ControlNVIDIA · International Journal of Artificial Intelligence1 citationDec 23, 2025Algebraic cryptanalysis of symmetric ciphers: modeling and multistep solving strategiesTechnology Innovation Institute · Serdica Mathematical Journal1 citationDec 23, 2025Generative Latent Coding for Ultra-Low Bitrate Image CompressionMicrosoft · arXiv (Cornell University)Dec 23, 2025Toward Intelligent Product Interaction: A Medium-Level Stimuli Toolkit Supporting AI-Powered Product Design Iteration and InnovationAlibaba · International Journal of Human-Computer InteractionDec 23, 2025EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-ExplorationAlibaba · arXiv (Cornell University)12 citationsDec 22, 2025KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised LearningMicrosoft · arXiv (Cornell University)11 citationsDec 22, 2025From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMsMicrosoft · arXiv (Cornell University)8 citationsDec 22, 2025Silent Data Corruption in Artificial Intelligence: A Growing Challenge for Large-Scale Machine LearningAlphabet, Meta, Microsoft, NVIDIA · IEEE Micro8 citationsDec 22, 2025PEAK: A Performance Engineering AI-Assistant for GPU Kernels Powered by Natural Language TransformationsMicrosoft · arXiv (Cornell University)6 citationsDec 22, 2025Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image ClassificationiFlytek · Arabian Journal for Science and Engineering4 citationsDec 22, 2025Vibe Reasoning: Eliciting Frontier AI Mathematical Capabilities -- A Case Study on IMO 2025 Problem 6Microsoft · arXiv (Cornell University)2 citationsDec 22, 20253DeepVOG: An Open-Source Framework for Real-Time, Accurate 3D Gaze Tracking with Deep LearningNVIDIA · Digital Biomarkers1 citationDec 22, 2025Selective LoRA for Visual Tokens and Attention HeadsLG AI Research · arXiv (Cornell University)Dec 22, 2025Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack DetectionMicrosoft · arXiv (Cornell University)Dec 22, 2025EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion TransformerAlibaba · arXiv (Cornell University)10 citationsDec 21, 2025A Study of Finetuning Video Transformers for Multi-view Geometry TasksMicrosoft · arXiv (Cornell University)Dec 21, 2025RecurGS: Interactive Scene Modeling via Discrete-State Recurrent Gaussian FusionHorizon Robotics · arXiv (Cornell University)2 citationsDec 20, 2025