Fine-tuning and adaptation

LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.

8,208 stories · RSS feed

arXiv Machine Learning

Jul 3

One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective

arXiv:2607. 02292v1 Announce Type: new Abstract: Neural quantum states (NQS) provide a flexible and scalable framework for approximating quantum many-body wavefunctions.

By Juan Agust\'in Duque, Sergio Garc\'ia Heredia, Vinicius Hernandes, Eli\v{s}ka Greplov\'a, Thomas Spriggs, Aaron Courville, Anna Dawid

reinforcement-learning fine-tuning

arXiv AI

Jul 3

Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness

arXiv:2510. 04484v2 Announce Type: replace-cross Abstract: The ability to control LLMs' emulated emotional states and personality traits is an essential step in enabling rich, human-centered interactions in socially interactive settings.

By Amin Banayeeanzade, Ala N. Tak, Fatemeh Bahrani, Anahita Bolourani, Leonardo Blas, Emilio Ferrara, Jonathan Gratch, Sai Praneeth Karimireddy

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jul 3

QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs

arXiv:2602. 10431v4 Announce Type: replace Abstract: Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment.

By Kanghyun Noh, Jinheon Choi, Yulhwa Kim

llms fine-tuning efficiency benchmarks

arXiv AI

Jul 3

Decomposer: Learning to Decompile Symbolic Music to Programs

arXiv:2607. 01849v1 Announce Type: cross Abstract: Musical performance involves executing a set of high-level musical instructions, yet recovering those instructions from the performance is a challenging inverse problem.

By Yewon Kim, Apurva Gandhi, David Chung, Graham Neubig, Chris Donahue

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 3

MMIR-TCM: Memory-Integrated Multimodal Inference and Retrieval for TCM Clinical Decision Support

arXiv:2607. 01814v1 Announce Type: new Abstract: Traditional Chinese Medicine (TCM) diagnosis, particularly through tongue inspection, faces persistent challenges in subjectivity and reproducibility.

By Lihui Luo, Joongwon Chae, Ziyan Chen, Yang Liu, Siyi Cheng, Weihan Gao, Zelin Zeng, Xiaoming Yin, Samaneh Beheshti Kashi, Dongmei Yu, Lian Zhang, Jing Sui, Zeming Liang, Jiansong Ji, Peter E. Lobie, Peiwu Qin

llms rag computer-vision fine-tuning multimodal benchmarks

arXiv AI

Jul 3

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

arXiv:2607. 02010v1 Announce Type: new Abstract: Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time.

By Qianyu Chen, Ziteng Feng, Canran Xiao, Runxuan Tang

llms fine-tuning multimodal

arXiv AI

Jul 3

Scaling Trends for Lie Detector Oversight in Preference Learning

arXiv:2607. 01567v1 Announce Type: new Abstract: Deceptive behavior in LLMs is costly to monitor and prevent, motivating approaches such as Scalable Oversight via Lie Detectors (SOLiD) (Cundy & Gleave, 2025), which uses lie detectors to identify responses for review by high-cost labelers.

By Oskar J. Hollinsworth, Ann-Kathrin Dombrowski, Sam Adam-Day, Adam Gleave, Chris Cundy

llms fine-tuning

arXiv AI

Jul 3

Multi-modal Rail Crossing Safety Analysis

arXiv:2607. 01365v1 Announce Type: cross Abstract: Given one or more images of a railway crossing, can we leverage visual cues that allow us to robustly estimate how safe it is?

By Paimon Goulart, Chansong Lim, N\'icolas Roque dos Santos, Yue Dong, Sheldon Peterson, Jia Chen, Evangelos E. Papalexakis

fine-tuning multimodal safety

arXiv AI

Jul 3

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence

arXiv:2604. 08169v2 Announce Type: replace Abstract: Alignment in LLMs is more brittle than commonly assumed: misalignment can be induced by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization.

By Niklas Herbster, Martin Zborowski, Alberto Tosato, Gauthier Gidel, Tommaso Tosato

llms agents fine-tuning benchmarks safety

arXiv Machine Learning

Jul 3

An Additive MLP-GNN Framework for Characterizing Chemical and Structural Contributions to Aqueous Solubility

arXiv:2607. 02212v1 Announce Type: cross Abstract: Aqueous solubility is a key property in early-stage drug discovery, but most predictive models merge physicochemical descriptors and molecular graph information into a single representation, obscuring whether a prediction is driven by global chemistry, molecular structure, or both.

By Sampreeti Bhattacharya, Arkaprava Roy

rag fine-tuning

arXiv AI

Jul 3

EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning

arXiv:2607. 01789v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale efficiently but remain costly to adapt due to redundant experts and uniform parameter allocation.

By Ahin Lee, Sehyun Yun, Taesik Gong

fine-tuning

arXiv Machine Learning

Jul 3

Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control

arXiv:2604. 08580v2 Announce Type: replace-cross Abstract: Reward fine-tuning of diffusion and flow models and sampling from tilted or Boltzmann distributions can both be formulated as stochastic optimal control (SOC) problems, where learning an optimal generative dynamics corresponds to optimizing a control under SDE constraints.

By Carles Domingo-Enrich, Jiequn Han

diffusion fine-tuning

arXiv AI

Jul 3

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail

arXiv:2607. 02072v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts.

By Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan

llms rag fine-tuning efficiency benchmarks safety

arXiv AI

Jul 3

Token Geometry

arXiv:2607. 01455v1 Announce Type: cross Abstract: Language models learn continuous programs over discrete symbols, with the embedding table and LM-head acting as the read/write interface between them.

By Kathan Shah

llms rag reinforcement-learning fine-tuning

arXiv AI

Jul 3

Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoning

arXiv:2512. 14157v2 Announce Type: replace Abstract: Recent medical MLLMs have made significant progress in generating step-by-step textual reasoning chains.

By Yankai Jiang, Yujie Zhang, Peng Zhang, Wenjie Li, Yichen Li, Jintai Chen, Xiaoming Shi, Shihui Zhen

agents computer-vision reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jul 3

TUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27B

arXiv:2607. 01927v1 Announce Type: cross Abstract: This paper presents TUDUM (T\"urk\c{c}e D\"u\c{s}\"unen \"Uretken Model), a project pipeline for adapting a Qwen-family 27B thinking model toward Turkish reasoning.

By Baran Bingol, Bahaeddin Turkoglu

reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 3

AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanations

arXiv:2607. 01934v1 Announce Type: cross Abstract: This work introduces AIriskEval-edu-db2, a new dataset designed to train and evaluate auditors based on LLMs for an explainable pedagogical risk assessment in instructional content for grades K-12.

By Javier Irigoyen, Roberto Daza, Francisco Jurado, Julian Fierrez, Ruben Tolosana, Alvaro Ortigosa, Enrique Blas, Aythami Morales

llms fine-tuning benchmarks safety

arXiv AI

Jul 3

Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training

arXiv:2607. 02118v1 Announce Type: new Abstract: Scientific Fitness Coaching (SFC) is typically delivered by human professionals, making it costly and inaccessible to many.

By Xingtao Zhao, Tian Yang, Han Jiang

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 3

AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models

arXiv:2607. 02269v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG).

By Rintaro Otsubo, Ryo Fujii, Reina Ishikawa, Taiki Kanaya, Kanta Sawafuji, Hiroki Kajita, Shigeki Sakai, Hideo Saito, Ryo Hachiuma

llms fine-tuning multimodal benchmarks

arXiv AI

Jul 3

Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens

arXiv:2507. 02964v2 Announce Type: replace-cross Abstract: The increasing scale of AI workloads demands High-Performance Computing (HPC) infrastructure and training methodologies that are both scalable and sustainable.

By Salahuddin Salahuddin, Ahmed Hussain, Jussi L\"opp\"onen, Toni Jutila

llms fine-tuning benchmarks

Get the daily briefing