Tech Times

ICML 2026 Opens in Seoul Next Week: Record 23,918 Submissions Signal AI Agent Safety Era

ICML 2026 opens in Seoul on July 6 with a record 23,918 submissions — more than double last year — and a research program ...

When the Model Is Confident and Wrong: A Practitioner Guide to LLM Output Reliability

The model learns that hedging is a signal of lower-quality output. This creates a systematic bias toward sounding certain.
IEEE

Reinforcement Learning Based Energy-Efficient Collaborative Inference for Mobile Edge Computing

Abstract: Collaborative inference in mobile edge computing (MEC) enables mobile devices to offload the computation tasks for the computation-intensive perception services, and the inference policy ...
IEEE

Characterizing Cloud-Native LLM Inference at Bytedance and Exposing Optimization Challenges and Opportunities for Future AI Accelerators

Abstract: As a major provider of LLM inference services, ByteDance has continuously explored diverse accelerator options to meet the rapidly growing inference demands of various heterogeneous LLM ...