LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2608.23256v1 Announce Type: new Abstract: Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reason...
arXiv:2608.23475v1 Announce Type: new Abstract: As large language models are increasingly used in data-scarce and evolving task scenarios, few-shot in-context learning (ICL) has become a key paradigm...
arXiv:2608.22215v1 Announce Type: new Abstract: Large language model (LLM) agents operate in dynamic environments where knowledge continuously evolves. Existing memory systems typically treat externa...
arXiv:2608.21440v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have advanced end-to-end autonomous driving by leveraging foundation models for semantic reasoning and long-tail...
arXiv:2608.23253v1 Announce Type: cross Abstract: Vision-language models typically encode an image into hundreds of visual tokens, incurring substantial inference latency and GPU memory overhead. Exi...
arXiv:2511.22281v2 Announce Type: replace Abstract: Observing certain patches in an image reduces the uncertainty of others. Their realization lowers the distribution entropy of each remaining patch...
arXiv:2608.21714v1 Announce Type: new Abstract: Recent page-image retrievers such as ColPali have improved retrieval over visually rich documents, yet little is known about how they behave in cross-l...
OVIBench introduces the first standardized benchmark for evaluating vision‑language models on Online Video Question Answering under Interruption, a realistic setting where users can interrupt the model during answer generation. The benchmark categorizes interruptions into Cancellation, False Trigger, and Correction, supports both open‑ended and multiple‑choice tasks, and provides an offline simulation protocol plus a multi‑dimensional metric suite. Experiments show that OVIBench can distinguish models’ interruption‑handling abilities, particularly in following correction requests, and that fine‑tuning on the newly created OVI‑Train dataset yields significant performance gains.
arXiv:2608.21606v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating whet...
arXiv:2608.22102v1 Announce Type: cross Abstract: We present GCA (Gaussian Constitutive Alignment), a framework for learning implicit constitutive laws from monocular dynamic video of deformable obje...
arXiv:2512.17730v2 Announce Type: replace Abstract: Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specif...
arXiv:2608.23329v1 Announce Type: cross Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video a...
arXiv:2608.23476v1 Announce Type: new Abstract: Narrow fine-tuning on small, domain-specific datasets can produce broad and surprising changes in model behavior-a phenomenon called weird generalizati...
arXiv:2608.22483v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly support decision-making in high-stakes domains, but they often hallucinate and express confidence that is mis...
arXiv:2608.22085v1 Announce Type: new Abstract: Synthetic clinical data generation with large language models addresses the scarcity that limits cancer staging research, but oncology hallucinations a...
arXiv:2608.22188v1 Announce Type: cross Abstract: Split Federated Fine-tuning (SFF) is a promising paradigm for scaling Large Language Models (LLMs) by partitioning model depth between resource-const...
arXiv:2608.15763v2 Announce Type: replace Abstract: AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low lat...
The paper introduces a Cross-Subject Perceived Speech Decoding (CPSD) framework that tackles the challenge of decoding perceived speech from non‑invasive brain recordings across different subjects. CPSD uses a two‑stage training process: first, contrastive learning pre‑trains a source model on multiple subjects to capture shared representations; second, personal specialization fine‑tunes the model for a target subject by extracting consistent components and further training on that subject’s data. A Positional Encoding‑based Spatial Attention (PESA) module is added to remap MEG/EEG data into a standardized reference space, improving cross‑subject consistency. Evaluations on three datasets (Armeni 2022, PKUEEG 2025, Broderick 2018) show that CPSD outperforms baseline methods by more than 6.8%, 15.4%, and 15.8% in Top‑10 accuracy, demonstrating its effectiveness, efficiency, and robustness.
arXiv:2608.23497v1 Announce Type: new Abstract: Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving wit...
The paper investigates how preference tuning—optimizing language models with explicit preference signals—behaves when applied to new domains. It systematically compares five alignment objectives and several adaptation strategies, such as target‑domain supervised fine‑tuning and pseudo‑labeling, across summarization, question‑answering helpfulness, and safety tasks. Results show that while pseudo‑labeling reduces domain‑shift degradation, it also causes mode collapse, highlighting a trade‑off between generalization and diversity.