vllm-triton-backend: How to get state-of-the-art performance on NVIDIA and AMD with just tritonBurkhard RingleinThomas Parnellet al.2025PyTorch Conference 2025
PyTorch Native Online Dynamic Reward Based Data Mixing FrameworkAmal Joe R SMehant Kammakomatiet al.2025PyTorch Conference 2025
When in Doubt, Cascade: Towards Building Efficient and Capable GuardrailsManish NagireddyInkit Padhiet al.2025AIES 2025
Exposing AI Bias by Crowdsourcing: Democratizing Critique of Large Language ModelsHangzhi GuoPranav Venkitet al.2025AIES 2025
Highlight All the Phrases: Enhancing LLM Transparency through Visual Factuality IndicatorsHyo Jin DoRachel Ostrandet al.2025AIES 2025
Hide or Highlight: Understanding the Impact of Factuality Expression on User TrustHyo Jin DoWerner Geyer2025AIES 2025
TerraMind: Large-Scale Generative Multimodality for Earth ObservationJohannes JakubikFelix Yanget al.2025ICCV 2025
Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference EnvironmentsNikoleta IliakopoulouJovan Stojkovicet al.2025MICRO 2025