arXiv Computation and Language August 21, 2026 By Ting-Wei Li, Sirui Chen, Jiaru Zou, Yingbing Huang, Tianxin Wei, Jingrui He, Hanghang Tong

EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation

Read the original on arXiv Computation and Language →

arXiv:2604. 26170v2 Announce Type: replace Abstract: Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge.

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 Computation and Language.

arXiv AI

Jun 24

Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models

arXiv:2606. 24841v1 Announce Type: new Abstract: Prompt-based learning has emerged as a dominant paradigm in natural language processing.

By Ahmad Pouramini, Hesham Faili

llms nlp fine-tuning

arXiv AI

Jun 16

Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning

arXiv:2510. 16882v4 Announce Type: replace-cross Abstract: Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks.

By Heming Zou, Yixiu Mao, Yun Qu, Qi Wang, Xiangyang Ji

llms rag fine-tuning benchmarks safety

arXiv Machine Learning

Jul 7

LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

arXiv:2607. 04733v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities.

By Yueyang Wang, Baolong Bi, Shuo Lu, Jingyuan Zhang

llms fine-tuning multimodal

arXiv AI

Jul 7

Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning

arXiv:2607. 03453v1 Announce Type: cross Abstract: Inference-time alignment methods, such as Best-of-$N$, offer a flexible alternative to training-based alignment by using reward models to select high-quality responses generated by a reference LLM.

By Eric Lei, Hsiang Hsu, Chun-Fu Chen

llms benchmarks safety

arXiv AI

Jul 14

Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals

arXiv:2607. 11505v1 Announce Type: cross Abstract: Post-training is essential for refining the domain-specific capabilities of large language models (LLMs), yet existing reward optimization and distribution matching methods tightly couple policy exploration with distribution alignment.

By Daocheng Fu, Rong Wu, Yu Yang, Xuemeng Yang, Jianbiao Mei, Licheng Wen, Pinlong Cai, Yong Liu, Botian Shi, Yu Qiao

llms safety

arXiv Computer Vision

1d ago

Beyond Discrete Samples: High Information Density Replay for Efficient Lifelong Person Re-Identification

The paper introduces HiDeR, a High Information Density Replay framework for Lifelong Person Re-Identification that replaces discrete sample selection with information compression. It uses a complexity‑aware memory allocation based on intra‑class variance and a metric‑guided condensation objective to preserve essential identity topologies, while a cross‑modality adaptation strategy bridges synthetic and real styles to improve training. Experiments show HiDeR outperforms state‑of‑the‑art methods in knowledge retention and generalization, and reduces cumulative replay cost.

By Mingyu Wang, Wei Jiang, Haojie Liu, Zhiyong Li, Weijie Mao

benchmarks

One email a morning, machine-written

Related stories

Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models

Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning

LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning

Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals

Beyond Discrete Samples: High Information Density Replay for Efficient Lifelong Person Re-Identification