LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2609.15022v1 Announce Type: new Abstract: Defense is a knowledge-intensive domain that requires precise understanding of specialized terminology, doctrinal concepts, operational procedures, and...
arXiv:2609.15886v1 Announce Type: new Abstract: Large language models (LLMs) often learn both desirable and undesirable properties during post-training. We study whether midtraining, an earlier train...
arXiv:2609.13486v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning decoder-only large language models (LLMs) for retrieval yields strong first-stage retrievers, with effectivene...
arXiv:2609.14060v1 Announce Type: cross Abstract: Quantization is one of the default deployment paths for open-weight LLM agents, but it is not behavior-preserving: an adversary can release a full-pr...
arXiv:2609.14485v1 Announce Type: new Abstract: Retrieval-Guided Fine-Tuning (RAG-FT) incorporates retrieved data directly into the training objective, but the statistical consequences of noisy retri...
The paper introduces a multimodal foundation model for lunar remote sensing, trained from scratch on SomBench—a dataset of nearly two million co‑registered tile bundles across 11 modalities at 1 m and 100 m resolutions. The model extends the TerraMind masked‑token architecture with lunar‑specific features such as explicit acquisition geometry and joint training of two spatial scales, and employs FlexiViT patch embeddings for adaptable patch sizes. Evaluation on crater detection, irregular mare patch segmentation, and polar ice prospectivity regression shows that the pretrained model matches or surpasses ImageNet‑pretrained baselines, with notable label efficiency and effective adaptation via LoRA.
KnowBench is a new benchmark for clinical AI that measures Effort Reduction (ER), the proportion of system-generated clinical work product accepted by clinicians after expert and safety review. The metric is applied uniformly across various administrative tasks—visit notes, billing codes, orders, EHR summarization, patient summaries, and decision support—using the clinician’s review-and-attestation as ground truth. An initial deployment of Knowtex’s models achieved an aggregate ER of 97.99% across more than one million encounters in six months, with specialty-specific ER ranging from 96.8% to 98.9%.
arXiv:2404.00727v3 Announce Type: replace Abstract: All state-of-the-art coreference resolution (CR) models involve finetuning a pretrained language model. Whether the superior performance of one CR...
arXiv:2609.14998v1 Announce Type: new Abstract: Recent work shows that models that learn to reward hack on RL environments can become broadly misaligned, and that reframing reward hacking as acceptab...
HISPO introduces a segment‑level policy‑optimization technique for reinforcement learning with verifiable rewards, creating entropy‑derived contiguous segments during rollout and applying clipped importance‑sampling correction at this granularity. It bridges the gap between token‑level and sequence‑level corrections, offering a middle‑ground approach for credit assignment in long‑form mathematical reasoning. Evaluated on Qwen3‑1.7B‑Base across six benchmarks, HISPO consistently outperforms or matches the strongest baselines in Pass@8 and Acc@8 metrics, notably improving AIME25 scores over GRPO and GSPO.
The paper presents a system for the MedReason 2026 challenge that tackles both multiple‑choice and open‑ended medical visual question answering using offline, containerized inference. Key findings include that comparing answer semantics rather than labels boosts retrieval‑only accuracy from 20.0 % to 57.5 % on a 200‑case holdout, and that varying the number of in‑prompt retrieved examples has minimal impact on final accuracy (93.5 %–94.0 %). The final system achieves 94.0 % MCQ accuracy on the development set and 93.20 % on the official pre‑evaluation, far surpassing the off‑the‑shelf baseline. "whyItMatters":"The results demonstrate that semantic‑aware retrieval and careful adapter tuning can dramatically improve medical VQA performance, offering a practical approach for high‑accuracy, offline inference in clinical settings."
arXiv:2609.15344v1 Announce Type: new Abstract: We study the adaptation of pretrained language models to univariate time-series forecasting through a parameter-efficient transfer learning framework,...
arXiv:2506.24092v3 Announce Type: replace Abstract: Adapting large pretrained vision models to medical image classification is often limited by memory, computation, and task-specific specializations....
arXiv:2609.13259v1 Announce Type: cross Abstract: Virtual Try-On (VTON) aims to dress a person with the reference garment, producing visually reasonable results aligned with human preferences. Turnin...
arXiv:2609.13226v1 Announce Type: new Abstract: Machine learning for neglected tropical diseases is limited by data, not algorithms: public annotated image sets for leprosy (Hansen's disease) number...
The paper presents a study on fine‑tuning open‑source instruction‑tuned language models for a Linear Control Systems course using LoRA. A dataset of 360 system‑user‑assistant conversations was created, and LoRA was applied to Qwen2.5‑3B‑Instruct and Qwen2.5‑7B‑Instruct with ranks r=4, 8, and 16. Evaluation with ROUGE, BERTScore, and structured‑output metrics showed that LoRA improved similarity and stability, with the 7B‑r16 model achieving the highest scores and r=8 offering a good trade‑off between performance and parameter efficiency.
arXiv:2609.13264v1 Announce Type: cross Abstract: Generating human-centric videos that preserve both visual identity and person-specific expressive behavior remains a fundamental challenge. In additi...
arXiv:2609.14284v1 Announce Type: new Abstract: Criterion-level grading connects examination performance to learning outcomes, but manual marking introduces workload and variation between markers. Th...
The paper introduces Drift-Constrained Optimization (DCO), a framework that treats behavioral drift during fine‑tuning of instruction models as a bounded constraint rather than an uncontrolled side effect. By defining a drift budget, the authors reformulate fine‑tuning as a direction‑selection problem, showing that choosing different update directions can qualitatively change outcomes. Experiments on Qwen3 models demonstrate that carefully selected directions improve scientific reasoning and multilingual translation while preserving reasoning capabilities and general performance.
The paper presents a method for fine‑tuning a large language model (LLM) recommender to generate personalized, non‑harmful explanations for its recommendations. By training two LLM‑judge reward models and using constrained GRPO, the authors achieve a significant increase in the PASS rate for all three criteria, from 0.649 to 0.956 on their own judges and from 0.677 to 0.931 on an independent judge. The fine‑tuned model maintains its original recommendation performance, demonstrating that LLM‑based recommenders can be adapted to complex tasks without loss of effectiveness.