会员服务
GeoFidelity-Bench: Evaluating Segment-Level Geographic Fidelity in Text-to-Image Street-View Generation
Arxiv
0+阅读 · 6月22日
Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Making
Arxiv
0+阅读 · 6月23日
CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation
Arxiv
0+阅读 · 6月23日
Phoenix: Safe GitHub Issue Resolution via Multi-Agent LLMs
Arxiv
0+阅读 · 6月22日
SCOPE: Sequential Conformal Probing for Reliable OOD Rejection in LLM Services
Arxiv
0+阅读 · 6月19日
NOEM$^{3}$A: a Neuro-symbolic Ontology-Enhanced Method for Multi-intent understanding in Mobile Agents
Arxiv
0+阅读 · 6月20日
AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents
Arxiv
0+阅读 · 6月22日
Physics-governed executable modelling of triboelectric nanogenerators
Arxiv
0+阅读 · 6月22日
ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill
Arxiv
0+阅读 · 6月21日
Caching for Dollars, Not Hits: An Exact Offline Reference for Cloud-Egress Caching and the Crossover That Decides When It Pays
Arxiv
0+阅读 · 6月19日
A Peek Behind the Curtain: Using Step-Around Prompt Engineering to Identify Bias and Misinformation in GenAI Models
Arxiv
0+阅读 · 6月19日
When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models
Arxiv
0+阅读 · 6月20日
Concordia: JIT-Compiled Persistent-Kernel Checkpointing for Fault-Tolerant LLM Inference
Arxiv
0+阅读 · 6月22日
From Community Forums to Issue Trackers: A Moodle Case Study
Arxiv
0+阅读 · 6月18日
LLM-Based Generalizable Hierarchical Task Planning and Execution for Heterogeneous Robot Teams with Event-Driven Replanning
Arxiv
0+阅读 · 6月18日
参考链接
微信扫码咨询专知VIP会员
Top