会员服务
Multi-stage Flow Scheduling for LLM Serving
Arxiv
0+阅读 · 3月18日
OmniVLN: Omnidirectional 3D Perception and Token-Efficient LLM Reasoning for Visual-Language Navigation across Air and Ground Platforms
OmniVLN: Omnidirectional 3D Perception and Token-Efficient LLM Reasoning for Visual-Language Navigation across Air and Ground Platforms
Arxiv
0+阅读 · 3月18日
Federated Computing as Code (FCaC): Sovereignty-aware Systems by Design
Federated Computing as Code (FCaC): Sovereignty-aware Systems by Design
Arxiv
0+阅读 · 3月18日
TRiMS: Real-Time Tracking of Minimal Sufficient Length for Efficient Reasoning via RL
Arxiv
0+阅读 · 3月18日
inference-fleet-sim: A Queueing-Theory-Grounded Fleet Capacity Planner for LLM Inference
Arxiv
0+阅读 · 3月17日
Efficient Reasoning on the Edge
Arxiv
0+阅读 · 3月17日
ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models
Arxiv
0+阅读 · 3月17日
Learning to Recall with Transformers Beyond Orthogonal Embeddings
Arxiv
0+阅读 · 3月16日
Intrinsic Sequentiality in P: Causal Limits of Parallel Computation
Arxiv
0+阅读 · 3月17日
SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token
Arxiv
0+阅读 · 3月14日
DUET: Disaggregated Hybrid Mamba-Transformer LLMs with Prefill and Decode-Specific Packages
Arxiv
0+阅读 · 3月16日
Token Coherence: Adapting MESI Cache Protocols to Minimize Synchronization Overhead in Multi-Agent LLM Systems
Arxiv
0+阅读 · 3月16日
Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models
Arxiv
0+阅读 · 3月16日
Qubit-centric Transformer for Surface Code Decoding
Arxiv
0+阅读 · 3月16日
Nested Music Transformer: Sequentially Decoding Compound Tokens in Symbolic Music and Audio Generation
Arxiv
0+阅读 · 3月16日
参考链接
微信扫码咨询专知VIP会员
Top