arXiv:2606. 27743v1 Announce Type: cross Abstract: Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2606. 10706v1 Announce Type: cross Abstract: Resource constraints increasingly determine what can be trained, fine-tuned, and deployed in large language models (LLMs), yet efficiency is often studied through isolated techniques rather than as an interacting system of limits.
arXiv:2604. 07472v2 Announce Type: replace Abstract: Serving large language model (LLM) inference in cloud environments requires jointly optimizing model selection, GPU provisioning, parallelism configuration, and workload routing under latency, accuracy, memory, and budget constraints.
arXiv:2607. 03876v1 Announce Type: new Abstract: With the rise of small quantized GGUF-based language models and their increasing use for on-device inference tasks, we have seen the growing need for an approach capable of reliably delivering these models at scale even under severe memory bandwidth constraints such as those imposed by pure CPU implementations.
arXiv:2606. 09514v1 Announce Type: new Abstract: Large language models (LLMs) incur high inference cost due to their depth and parameter scale.
arXiv:2601. 22448v2 Announce Type: replace Abstract: RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts are sampled and when.
When2Think introduces a post‑training framework that dynamically allocates reasoning depth in Large Reasoning Models based on instance difficulty. The method uses Instance‑level Difficulty‑Aware Control (IDAC) to shape rewards with pre‑computed accuracy and token usage statistics, enabling stable, critic‑free optimization without learned reward models. Experiments on mathematical benchmarks show that When2Think improves accuracy‑efficiency trade‑offs, achieving higher Pass@3 scores while reducing token usage compared to baseline models.