NEURIPS 2025 "adaptive inference" Papers
2 papers found
Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
NEURIPS 2025posterarXiv:2509.23666
Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs
Hao Kang, Qingru Zhang, Han Cai et al.
NEURIPS 2025spotlightarXiv:2505.19481
4
citations