Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Coding Agents are Strong Prompt OptimizersMicrosoft · arXiv (Cornell University)Aug 13Machine Unlearning for Speech Question Answering in Large Audio-Language ModelsMeta · arXiv (Cornell University)Aug 13VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive AgentsNVIDIA · arXiv (Cornell University)Aug 13From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRLMicrosoft · arXiv (Cornell University)Aug 13AdsWorldEngine: A Self-Evolving Conversational Advertising Agent through Orchestrator and Tool CoevolutionMicrosoft · arXiv (Cornell University)Aug 13Mixture of Training: Recombining Small-Scale Scaffolded Pretraining Runs into a Larger Language ModelAlphabet · arXiv (Cornell University)Aug 13OpScale: Operator-level Provisioning and Autoscaling for LLM ServingMicrosoft · arXiv (Cornell University)Aug 13SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video AttentionAlibaba · arXiv (Cornell University)Aug 13Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical DiversityCohere · arXiv (Cornell University)Aug 13ATOBench: Tracing How Autonomous Penetration-Testing Agents Verify Vulnerabilities When Target Evidence LiesAlibaba · arXiv (Cornell University)Aug 13Structured Local Differential Modeling for AI-Generated Image DetectionAlibaba · arXiv (Cornell University)Aug 13HounsWorld: A Multimodal World Model for Hidden Patient-State Readout, Reconstruction, and SimulationAlibaba · arXiv (Cornell University)Aug 13Classical Simulation and Design Frontiers for IBM's Doped Clifford Sampling ExperimentNVIDIA · arXiv (Cornell University)Aug 13Potential Applications of HBF in LLM Serving SystemsAlibaba · arXiv (Cornell University)Aug 13Unifying Depth and Width Pruning for LLMs via Binary Knapsack OptimizationMicrosoft · arXiv (Cornell University)Aug 13Residual and Entropy Coding in AV2Alphabet · Proceedings - International Conference on Image ProcessingAug 13VLM-Dreamer: VLM-Imagined BI-Directional Inpainting for Single-Image 360 Scene GenerationNVIDIA · Proceedings - International Conference on Image ProcessingAug 13The in-Loop Filtering Pipeline in Av2Alphabet, NVIDIA · Proceedings - International Conference on Image ProcessingAug 13Machine Learning-Based Control of Local Warped Motion Compensation in the SVT-AV1 EncoderMeta · Proceedings - International Conference on Image ProcessingAug 13SelfVTON: Enhancing Virtual Try-On with Self-Supervised Cloth Detailing and Body AlignmentAlibaba · Proceedings - International Conference on Image ProcessingAug 13Overview of Transform Coding in AV2Alphabet · Proceedings - International Conference on Image ProcessingAug 13An Overview Of Inter Coding Tools in AV2Alphabet · Proceedings - International Conference on Image ProcessingAug 13Panoptic3d: Leveraging 3d Pseudo Supervision for Panoptic Occupancy PredictionMicrosoft · Proceedings - International Conference on Image ProcessingAug 13R-OVAR: Robust Open-Vocabulary Action Recognition for PracticalityAlibaba · Proceedings - International Conference on Image ProcessingAug 13Beyond Average FPS: Assessing ACR-HR vs. DCR for Frame Drop Severity and a Novel No-Reference MetricAlphabet · Proceedings - International Conference on Image ProcessingAug 13