Mechlands Vibe 99: A superb keyboard with one questionable layout decision
zmescience.com·13h
🧠BF16
Flag this post
Nvidia AI: A Revolutionary €1 Billion Boost For Germany's Digital Future
bitcoinworld.co.in·16h
🧠BF16
Flag this post
One-Second Voice-to-Voice Latency with Modal, Pipecat, and Open Models
modal.com·1d
🏎️TensorRT
Flag this post
Intel, Cisco Collaboration Delivers Industry’s First Systems Approach for AI Workloads at the Edge
newsroom.intel.com·15h
🔗NCCL
Flag this post
Announcing the fastest inference for realtime voice AI agents
together.ai·2d
🤖AI Coding Tools
Flag this post
AMD Ryzen 7 9700X3D Appears in Leaked PassMark Benchmark
techpowerup.com·15h
📈GPU Occupancy
Flag this post
Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
arxiv.org·2d
🔄ONNX
Flag this post
A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios
arxiv.org·2d
🎓Model Distillation
Flag this post
Intelligent Computing Social Modeling and Methodological Innovations in Political Science in the Era of Large Language Models
arxiv.org·2h
🎓Model Distillation
Flag this post
Auditing M-LLMs for Privacy Risks: A Synthetic Benchmark and Evaluation Framework
arxiv.org·2h
⚡ONNX Runtime
Flag this post
Variational Geometric Information Bottleneck: Learning the Shape of Understanding
arxiv.org·1d
🏎️TensorRT
Flag this post
Enhanced Block Copolymer Lithography via Adaptive Stochastic Gradient Descent and Dynamic Mask Optimization
⏱️Benchmarking
Flag this post
Automated Prompt Generation for Code Intelligence: An Empirical study and Experience in WeChat
arxiv.org·2h
🤖AI Coding Tools
Flag this post
T3: Test-Time Model Merging in VLMs for Zero-Shot Medical Imaging Analysis
arxiv.org·3d
🏎️TensorRT
Flag this post
MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
arxiv.org·2d
📊Gradient Accumulation
Flag this post
Loading...Loading more...