Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
DeblurDiff: Real-World Image Deblurring with Generative Diffusion ModelsSenseTime · arXiv (Cornell University)4 citationsFeb 6, 2025Adapting to Evolving Adversaries with Regularized Continual Robust TrainingAlphabet, Google DeepMind · arXiv (Cornell University)3 citationsFeb 6, 2025Multi-Label Test-Time Adaptation with Bound Entropy MinimizationAlibaba · arXiv (Cornell University)2 citationsFeb 6, 2025Composing Distributed Computations Through Task and Kernel FusionNVIDIA · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)2 citationsFeb 6, 2025Automatic Tracing in Task-Based Runtime SystemsNVIDIA · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)2 citationsFeb 6, 2025QExplorer: Large Language Model Based Query Extraction for Toxic Content ExplorationAlibaba · arXiv (Cornell University)Feb 6, 2025Re-CATA: Real-Time and Flexible Accelerator Design Framework for On-Device Codec AvatarsMeta · IEEE Transactions on Computer-Aided Design of Integrated Circuits and SystemsFeb 6, 2025Flips: A Flexible Partitioning Strategy Near Memory Processing Architecture for Recommendation SystemAlibaba · IEEE Transactions on Parallel and Distributed SystemsFeb 6, 2025The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information SteeringGoogle DeepMind · arXiv (Cornell University)40 citationsFeb 5, 2025Gaze Inputs for Targeting: The Eyes Have It, Not With a CursorMeta · International Journal of Human-Computer Interaction11 citationsFeb 5, 2025Scaling laws in wearable human activity recognitionAlphabet · arXiv (Cornell University)7 citationsFeb 5, 2025Building Bridges between Regression, Clustering, and ClassificationGoogle DeepMind · arXiv (Cornell University)4 citationsFeb 5, 2025TruePose: Human-Parsing-guided Attention Diffusion for Full-ID Preserving Pose TransferAlibaba · arXiv (Cornell University)2 citationsFeb 5, 2025YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image AlignmentMeta · arXiv (Cornell University)Feb 5, 20253D Gaussian Splatting: Survey, Technologies, Challenges, and OpportunitiesMicrosoft · IEEE Transactions on Circuits and Systems for Video Technology185 citationsFeb 4, 2025STAIR: Improving Safety Alignment with Introspective ReasoningAlibaba · arXiv (Cornell University)62 citationsFeb 4, 2025PolarQuant: Quantizing KV Caches with Polar TransformationAlphabet · arXiv (Cornell University)29 citationsFeb 4, 2025Generative Adversarial Networks for Dynamic Malware Behavior: A Comprehensive Review, Categorization, and AnalysisTechnology Innovation Institute · IEEE Transactions on Artificial Intelligence29 citationsFeb 4, 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal VerificationMeta · arXiv (Cornell University)28 citationsFeb 4, 2025Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-TuningMicrosoft · arXiv (Cornell University)11 citationsFeb 4, 2025Learning the RoPEs: Better 2D and 3D Position Encodings with STRINGAlphabet · arXiv (Cornell University)9 citationsFeb 4, 2025Avoiding spurious sharpness minimization broadens applicability of SAMGoogle DeepMind · arXiv (Cornell University)6 citationsFeb 4, 2025Discovering Quality-Diversity Algorithms via Meta-Black-Box OptimizationSakana AI · arXiv (Cornell University)6 citationsFeb 4, 2025Understanding Operational CDN Live Streaming: A Measurement Study on Performance, Costs, and EnhancementsAlibaba · IEEE Transactions on Circuits and Systems for Video Technology4 citationsFeb 4, 2025Diffusion Instruction TuningGoogle DeepMind · arXiv (Cornell University)1 citationFeb 4, 2025