Fine-tuning and adaptation

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

8,248 stories · RSS feed

arXiv Machine Learning

Jun 5

Automated Proving of Shannon-Type Entropy Inequalities via Fine-Tuned Language Models and Guided Tree Search

arXiv:2606. 05729v1 Announce Type: cross Abstract: Proving Shannon-type entropy inequalities is a fundamental task in information theory that often requires constructing non-trivial linear combinations of known constraints, which is a combinatorial search problem that scales poorly with the number of random variables.

By Shing Yin Wong, Shaocheng Liu, Linqi Song, Amin Gohari, Cheuk Ting Li

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 5

Is Diversity All You Need for Scalable Robotic Manipulation?

arXiv:2507. 06219v2 Announce Type: replace-cross Abstract: Data scaling has driven remarkable success in foundation models for Natural Language Processing (NLP) and Computer Vision (CV), yet the principles of effective data scaling in robotic manipulation remain insufficiently understood.

By Modi Shi, Li Chen, Jin Chen, Yuxiang Lu, Chiming Liu, Guanghui Ren, Ping Luo, Di Huang, Maoqing Yao, Hongyang Li

computer-vision nlp robotics fine-tuning

arXiv Machine Learning

Jun 5

State commitment learning: training language models to distinguish computation from memory

arXiv:2606. 05201v1 Announce Type: new Abstract: Reasoning language models do not distinguish tokens used for computation from tokens that constitute persistent state: once generated, all hidden thoughts remain in context and influence future predictions.

By Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao, Zijian Zeng, Huiming Yang

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 5

Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction

arXiv:2606. 06303v1 Announce Type: new Abstract: Controllable generation with discrete diffusion models is often hindered by high computational overhead or the need for retraining.

By Hongkun Dou, Zike Chen, Fengji Li, Hongjue Li, Yue Deng

diffusion fine-tuning benchmarks

arXiv Machine Learning

Jun 5

The Language of Elution: Autoregressive Prediction of the Next Feature in Untargeted LC-HRMS Lipidomics

arXiv:2606. 05225v1 Announce Type: cross Abstract: Untargeted liquid chromatography-high-resolution mass spectrometry (LC-HRMS) detects thousands of molecular features per sample, yet only 2-20% receive confident structural annotations.

By Dayanjan S. Wijesinghe

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 5

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

arXiv:2606. 05781v1 Announce Type: new Abstract: Deploying frontier large language models (LLMs) for domain-specific structured evaluation tasks often incurs substantial latency, cost, and data privacy overhead.

By Srinivasan Manoharan, Dilipkumar Nallusamy, Sachin Kumar, Haifeng Wu

llms fine-tuning safety

arXiv Machine Learning

Jun 5

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

arXiv:2512. 09706v2 Announce Type: replace Abstract: The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models.

By Kaichen He, Zihao Wang, Muyao Li, Anji Liu, Yitao Liang

agents reinforcement-learning robotics fine-tuning benchmarks

arXiv Machine Learning

Jun 5

Surrogate Neural Architecture Codesign Package (SNAC-Pack)

arXiv:2605. 16138v2 Announce Type: replace Abstract: Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost.

By Jason Weitz, Dmitri Demler, Benjamin Hawks, Aaron Wang, Nhan Tran, Javier Duarte

agents fine-tuning efficiency

arXiv Machine Learning

Jun 5

An accurate nucleic acid-small molecule docking framework via geometric deep learning with large-scale pretraining

arXiv:2606. 05198v1 Announce Type: cross Abstract: Nucleic acids are increasingly recognized as therapeutic targets beyond conventional protein-centered drug discovery, yet accurate and efficient docking of small molecules to nucleic acid structures remains challenging.

By Shi Li (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China), Xujun Zhang (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China), Mingquan Liu (Faculty of Health Sciences, University of Macau, Macau SAR, China), Hui Zhang (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China, Shanghai Innovation Institute, Shanghai, China), Shuoying Jia (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China, Shanghai Innovation Institute, Shanghai, China), Yu Kang (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China, Shanghai Innovation Institute, Shanghai, China), Tingjun Hou (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China, Zhejiang Provincial Key Laboratory for Intelligent Drug Discovery and Development, Jinhua Institute of Zhejiang University, Zhejiang, China), Peichen Pan (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China, Zhejiang Provincial Key Laboratory for Intelligent Drug Discovery and Development, Jinhua Institute of Zhejiang University, Zhejiang, China)

fine-tuning benchmarks

arXiv Machine Learning

Jun 5

ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interaction

arXiv:2512. 20111v2 Announce Type: replace-cross Abstract: As the time horizons of sequential decision-making tasks grow, keeping full interaction histories in model context becomes increasingly costly.

By Aly Lidayan, Jakob Bjorner, Satvik Golechha, Kartik Goyal, Alane Suhr

agents nlp reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 5

TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation

arXiv:2606. 06133v1 Announce Type: cross Abstract: TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols.

By Eric Spencer, Arslan Bisharat, Brian Ortiz, Khushboo Bhadauria, TaiNing Wang, George K. Thiruvathukal, Konstantin Laufer, Mohammed Abuhamad

llms reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jun 5

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

arXiv:2606. 05680v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the automatic synthesis (generation) of register-transfer level (RTL) code from natural language instructions, offering a promising pathway to accelerate chip design.

By Mohammad Akyash, Nowfel Mashnoor, Kimia Azar, Hadi Kamali

llms rag agents fine-tuning safety

Towards Data Science

Jun 4

Five Ways to Fine-Tune Chronos-2, the Time Series Foundation Model

In Part 1 of this series, we introduced Chronos-2, a time-series foundation model. We got our hands dirty by walking through a real case study and saw what Chronos-2 can do straight out of the box, with no training.

By Shuai Guo

fine-tuning

Hugging Face Trending Papers

Jun 4

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents

Language-model agents act through repeated cycles of observation, reasoning, and action selection, making safety monitoring depend on both internal model state and environment context. We study reward-hacking monitors in ReAct-style agents acting in Gameable ALFWorld and WebShop.

llms agents fine-tuning safety

Hugging Face Trending Papers

Jun 4

GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speech

We propose GLASS, a framework for composable acoustic style control in zero-shot autoregressive text-to-speech (TTS) that learns controls from post-generation rewards rather than style labels. In zero-shot TTS, a speaker prompt often entangles speaker identity with prosodic attributes such as speaking rate and pitch, making it difficult to change style without changing the prompt itself.

fine-tuning multimodal

Hugging Face Trending Papers

Jun 4

PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation

User interface (UI) and user experience (UX) evaluation is central to product development, yet reliable feedback still relies on recruiting human participants or running online A/B tests, making early-stage iteration slow and costly. In light of this, recent work has explored Multimodal Large Language Models as proxy evaluators.

llms agents fine-tuning multimodal

arXiv AI

Jun 4

Adaptive Minds: Empowering Agents with LoRA-as-Tools

arXiv:2510. 15416v2 Announce Type: replace Abstract: We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke.

By Pavan C Shekar, Aswanth Krishnan

llms agents fine-tuning benchmarks

arXiv AI

Jun 4

Overview of the EReL@MIR 2025 Multimodal Document Retrieval Challenge (Track 1)

arXiv:2606. 04240v1 Announce Type: cross Abstract: Retrieval over visually-rich documents, pages that interleave text with figures, tables, and charts, is essential for multimodal retrieval-augmented generation, yet most retrievers still discard the visual channel.

By Jingbiao Mei

llms rag fine-tuning multimodal

arXiv AI

Jun 4

R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search

arXiv:2606. 04823v1 Announce Type: new Abstract: Large language models (LLMs) are fluent on open-ended tasks, yet in agentic settings, where a system must plan, use tools, and act over extended horizons, fluency does not ensure reliable delivery.

By Jo\~ao Pedro Gandarela, Thiago Rios, Stefan Menzel, Andr\'e Freitas

llms agents robotics fine-tuning safety

arXiv AI

Jun 4

A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks

arXiv:2510. 24342v2 Announce Type: replace Abstract: Prior brain-AI alignment studies are typically constrained by specific inputs and tasks, limiting their ability to capture organizational properties across models with different modalities.

By Silin Chen, Yuzhong Chen, Caiwei Wang, Zifan Wang, Junhao Wang, Zifeng Jia, Keith M Kendrick, Tuo Zhang, Lin Zhao, Dezhong Yao, Tianming Liu, Xi Jiang

llms fine-tuning multimodal safety

Get the daily briefing