LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2601.11719v4 Announce Type: replace Abstract: Self-supervised learning, in the context of foundation model training, is a powerful pre-training method for learning feature representations witho...
arXiv:2609.21288v1 Announce Type: new Abstract: Surface electromyography (sEMG)-based silent speech interfaces are limited by cross-user variability and calibration burden. We study a limited-data se...
KnowDemo is a framework that generates diverse robot demonstrations from human videos by leveraging structured manipulation knowledge. It uses a vision‑language model to extract task requirements and permissible execution variations, then resolves these against target‑scene entities to guide candidate generation and screening before motion planning. The resulting demonstrations feature multimodal behavior, alternative contact strategies, and valid subtask orders, and have been shown to improve planning success and enable sim‑to‑real policy transfer across three tasks.
arXiv:2609.21039v1 Announce Type: new Abstract: A pervasive structural pattern in modern deep learning is the linear factorization block: a submodule of the form $W = BA$ in which two parameter matri...
OneBid is a unified auto‑bidding foundation model that consolidates diverse cost‑per‑X (oCPX) advertising scenarios into a single framework. It builds on Decision Transformer by conditioning on two atomic signals—Return‑to‑Go for conversion value and Cost‑to‑Go for cost ratio—and incorporates value‑aware regularization. A sequence‑level Mixture‑of‑Experts architecture captures cross‑scenario knowledge while preserving low latency, and a Critic‑guided Relative Offline Policy optimization (CROP) aligns the backbone with scenario‑specific preferences without unsafe online exploration. In production at Kuaishou, OneBid achieved a 2.2% overall ADVV increase and up to 13.1% in the ROAS scenario.
The paper examines whether fine‑tuning large language models (LLMs) with personality‑labelled data improves their ability to act as socially interactive agents. Two small open‑weight LLMs were fine‑tuned on a corpus of personality‑labelled social media posts and dialogues, and the resulting models were evaluated in various social interaction scenarios by independent LLM judges. The findings show that the fine‑tuned models do not outperform their baseline counterparts in role‑playing personalities, though they offer comparable text quality and increased linguistic diversity for the Qwen models; low inter‑rater agreement limits confidence in the results, suggesting future work should focus on training data quality and domain alignment.
The paper investigates the effect of using semantic positive pairs—different instances of the same class—in self‑supervised visual representation learning. By creating matched ImageNet‑1K subsets of augmented pairs and manually curated semantic pairs, the authors compare contrastive and non‑contrastive SSL methods under identical training conditions. Across transfer learning and object detection tasks, semantic‑pair pretraining consistently outperforms augmented‑pair pretraining, with contrastive methods like SimCLR showing the largest gains, indicating that semantic pairs foster additional invariances beyond standard augmentations.
The paper presents a three‑stage, parameter‑efficient approach to improve automatic target recognition (ATR) with synthetic aperture sonar (SAS) data by adapting DINOv3 Vision Transformers. Stage 1 applies Low‑Rank Adaptation (LoRA) while freezing the backbone, which significantly boosts the area under the precision‑recall curve from 0.300 to 0.679. Subsequent hard‑negative mining and supervised contrastive learning stages show negligible impact, indicating that a single LoRA adaptation is sufficient for effective underwater ATR.
arXiv:2606.03963v4 Announce Type: replace-cross Abstract: Deep reinforcement learning enables autonomous robots to learn complex navigation tasks, but still relies heavily on time consuming manual re...
Tracking neurite morphology over time helps characterize structural changes during neuronal development and deterioration, but long-term time-lapse imaging is resource-intensive and difficult to scale...
Monocular colonoscopic 3D reconstruction is important for surgical robotic colonoscopy, but remains challenging due to weak texture, specular reflections, limited view overlap, and non-rigid tissue mo...
Model-free reinforcement learning can acquire contact-rich robotic manipulation skills through trial-and-error interaction, but it often requires the policy to learn both task strategy and low-level m...
oMeBench is a large-scale, expert-curated benchmark designed to evaluate large language models (LLMs) on organic mechanism reasoning. It contains over 10,000 annotated mechanistic steps, including reaction type labels, intermediate structures, and difficulty ratings, and introduces the oMeS scoring framework to assess logical consistency and chemical structural similarity. Evaluation shows that while current LLMs display promising chemical intuition, they often fail to produce correct and consistent multi-step reasoning, though prompting and fine-tuning can bring smaller models up to the level of closed‑source frontier models.
The paper introduces Live-ProsodyJudge (LPJ), a cost‑effective pairwise evaluator distilled from Gemini for assessing fine‑grained prosody in live streaming TTS. It identifies a flaw called verdict coupling, where multi‑dimensional scores collapse into a single preference, and proposes Decoupled‑Live‑ProsodyJudge (D‑LPJ) to eliminate this issue through masking and a span‑local GRPO strategy. Experiments show LPJ outperforms a single Gemini call in accuracy, and D‑LPJ provides independent dimension judgments, achieving high alignment with human top‑3 selections in a TTS candidate tournament.
GAPrompt++ is a multi-granular geometry-aware prompting method designed to adapt pre-trained 3D vision models to downstream tasks efficiently. It introduces a Point Shift Prompter for multi-scale geometric feature extraction, a Keypoint Prompter for local geometric saliency, and a Prompt Propagation mechanism to embed these cues throughout the model hierarchy. Experiments demonstrate that GAPrompt++ outperforms other prompting-based PEFT methods and even surpasses full fine-tuning while using less than 2% trainable parameters, and the authors provide two new challenging benchmarks for future research.
The paper introduces pre‑trained models for extracting variant‑phenotype relations from biomedical text, focusing on the SNPPhenA corpus. Fine‑tuning small BERT‑based models, especially DeBERTa, achieves performance close to the current state‑of‑the‑art. Moreover, careful fine‑tuning of Google’s Gemini Pro 1.0 surpasses existing benchmarks on both sentence‑level and abstract‑level relation extraction tasks.
The paper introduces an AI-assisted pipeline for retrieving goldsmith marks from silverware images, combining mark localization with metric‑learning fine‑tuning on three backbone models (ResNet‑50, ViT‑S/16, and DINOv2 ViT‑S/14). Systematic tests of cropping strategies show that manual cropping and metric‑learning fine‑tuning yield the best performance, with DINOv2 ViT‑S/14 achieving 62.63% mAP and 73.74% Top‑1 accuracy. The authors release a manually annotated dataset, code, and a public web interface to support reproducibility and adoption in digital humanities.
The paper adapts the compact PP‑OCRv6 recognizer for historical text recognition and compares it to a conventional CRNN across various training regimes, including generalized pretraining, domain‑specific training, corpus‑level fine‑tuning, and manuscript‑specific few‑shot adaptation on multilingual Latin and Arabic scripts. While PP‑OCRv6 does not always beat the CRNN when trained from scratch, heterogeneous pretraining significantly improves its generalization. Additionally, fine‑tuned PP‑OCRv6 can surpass a large vision‑language model (Qwen3.5‑based Medusa) that is specifically tailored for historical Latin‑script handwriting recognition.
UniExo is a framework that builds a single, multi-skill musculoskeletal human policy by distilling four imitation experts—walking, turning, running, and backward walking—into one network guided by a skill latent. The human policy is fine‑tuned with reinforcement learning on transition sequences, achieving a 94.7% tracking success rate on unseen clips and greater robustness to perturbations. A hip exoskeleton controller is then co‑adapted with this human policy via multi‑agent reinforcement learning, enabling it to assist across four treadmill speeds and a continuous route of all four skills without explicit mode switching.
CellRFT is a reinforcement fine‑tuning framework designed to improve single‑cell perturbation modeling by directly optimizing biological evaluation metrics. It employs policy‑gradient methods to learn from non‑differentiable biological rewards and aggregates multiple rewards hierarchically. Experiments show that CellRFT enhances perturbation prediction across various pretrained models and reveals interactions between different biological criteria, suggesting new ways to shape model behavior and evaluation design.