arXiv AI
Fine-Tuning Small Language Models for Reliable VASP INCAR Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 24
Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
arXiv:2603. 15510v2 Announce Type: replace Abstract: The synthesis of inductive loop invariants remains a critical bottleneck in automated program verification.
arXiv Computation and Language
Sep 22
LLM-Based FORM Code Generation with Verification-Driven Fine-Tuning
arXiv:2609.23367v1 Announce Type: cross Abstract: FORM is a domain-specific symbolic manipulation language widely used in particle physics for processing the very large algebraic expressions arising...
arXiv AI
Jun 3
Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines
arXiv:2605. 25645v2 Announce Type: replace-cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation.
arXiv AI
Jul 13
Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations
arXiv:2607. 09172v1 Announce Type: cross Abstract: Large Language Models are reshaping how software is developed and maintained.
arXiv AI
Oct 9
RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation
RaReCache is a framework that allows a large target language model to decode accurately from a KV cache prefilled by a much smaller source model by selectively recomputing only critical token positions. It identifies these positions using a rank disagreement metric that scores tokens based on the energy of their mapped KV in output directions weakly supported by calibration data. Across two model families and five benchmarks, RaReCache achieves up to a 3.04× prefill speedup and significantly reduces prefill latency while maintaining 95–99% of target accuracy with a 30–40% recompute budget.
arXiv Machine Learning
Aug 31
Parser States Already Know: Structure-Conditioned KV Persistence for Structured Generation
The paper introduces PASK (Parser-Aware Structural KV Persistence), a method that leverages parser transitions to inform key‑value (KV) persistence decisions in structured generation tasks. By aligning KV compression with task‑level structured risk, PASK sets protection floors based on error sensitivity and allocates remaining KV capacity using attention‑output distortion, producing a lightweight, structure‑conditioned lookup policy. In experiments on Qwen3‑4B, PASK achieves a 17.39‑point accuracy gain over the best compressed baseline, while delivering up to 2.2× higher throughput, 3.3× lower TPOT, and 0.53× the peak GPU memory of full KV.