Risk-Controlled KV-Cache Eviction: From Memory Budgets to Risk Targets

YesterdayReported by arXiv36

Risk-Controlled KV-Cache Eviction: From Memory Budgets to Risk Targets. It centres on Inference, and also names Llama and Mistral AI. Reported by arXiv. Bharat Hunt files it under AI Models and AI Regulation — the section covering a new or updated model, its capabilities, benchmarks or availability.

Written by Bharat Hunt from the headline and the coverage below. The original reporting is the source of truth.

Read original coverage

Companies, models and people in this story

Reported by arXiv

First seen yesterday

arXivRisk-Controlled KV-Cache Eviction: From Memory Budgets to Risk TargetsYesterdayBeomgu Kang

AI Models39

Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following

Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following. It centres on Fine-tuning, and also names Benchmarks and Llama. Reported by arXiv. Bharat Hunt files it under AI Models and AI Research — the section covering a new or updated model, its capabilities, benchmarks or availability.

arXivYesterday

AI Models38

Learning the Cost of Reliable Inference

Learning the Cost of Reliable Inference. It centres on Inference, and also names Llama and Qwen. Reported by arXiv. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability.

← All AI stories

Risk-Controlled KV-Cache Eviction: From Memory Budgets to Risk Targets

Companies, models and people in this story

Reported by arXiv

Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following

Learning the Cost of Reliable Inference

Computation Over Geometry: Meaning Identity Is Computed, Not Shipped in the Embeddings

Tensor Decomposition of Transformer Key-Value Caches: Spectral Structure and Format Comparison

Companies, models and people in this story

Reported by arXiv

Related AI coverage

Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following

Learning the Cost of Reliable Inference

Computation Over Geometry: Meaning Identity Is Computed, Not Shipped in the Embeddings

Tensor Decomposition of Transformer Key-Value Caches: Spectral Structure and Format Comparison