LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2603.08166v2 Announce Type: replace Abstract: Automated Drug Combination Extraction (DCE) from large-scale biomedical literature is crucial for advancing precision medicine and pharmacological...
arXiv:2603.16932v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational ef...
NV-Reason-CT is a generative vision‑language model designed for chest and abdominal CT analysis that preserves native 3D visual encoding and incorporates radiologist‑guided reasoning. The system couples a 3D vision transformer with a language model, feeding all visual tokens and their 3D coordinates directly into language decoding to maintain volumetric spatial information. Trained on a curated corpus of about 550,000 multimodal instruction examples, the model supports abnormality classification, report generation, and interactive reasoning, achieving strong performance on CT benchmarks and reducing expert interpretation time by 50%.
The paper studies matrices built from block‑diagonal factors interleaved with fixed permutations, a structured family useful in deep learning for balancing expressivity and efficiency. By applying Riemannian geometry, the authors determine when this class forms a smooth manifold and develop Riemannian tools for the orthogonal two‑factor case. They propose efficient algorithms that use automatic differentiation, allow parameter sharing, and avoid dense matrix construction, testing them on matrix approximation and fine‑tuning large language models, while also exploring properties of factorizations with more factors.
arXiv:2609. 27303v1 Announce Type: new Abstract: Livestreams are long-lasting interactive environments where audiovisual content, viewer activity, host behavior, and platform signals evolve together, creating assistance needs that emerge from the stream itself.
The paper "When Context Misleads: In-context Learning with Jurisdiction in Large Language Models" introduces FakeContextBench, a benchmark of pseudoscientific claims across seven domains to test large language models’ ability to judge whether contextual information should dictate the answer. Experiments show that both commercial and open‑source models struggle with context authority and that standard ICL fine‑tuning can worsen susceptibility to misleading context. The authors propose Jurisdiction In‑Context Learning (J‑ICL), a post‑training framework that adds context validation to the objective, which improves benchmark scores and reality accuracy by significant margins over baseline models.
The paper proposes a two‑stage framework that first fine‑tunes a large language model (LLM) and then rectifies its outputs, allocating limited labeled data optimally between the stages. It argues that the usual mean‑squared‑error objective for fine‑tuning misaligns with the downstream rectification, and instead suggests minimizing prediction‑error variance for mean estimation or a scalarized variance metric for general M‑estimation. Empirical results confirm that this variance‑based fine‑tuning, combined with optimal data allocation, yields significant efficiency gains over using either fine‑tuning or rectification alone, or using the conventional objective.
The paper proposes that self‑improvement methods for language models—such as debate, bootstrap, and internal coherence maximization—can be unified under a framework called coherence optimization. This framework seeks a context‑to‑behavior mapping that is most compressible and jointly predictable, and the authors prove its equivalence to description‑length regularization. They further show that coherence regularization, when guided by a pretrained model prior, optimizes a lower bound on worst‑case accuracy for semi‑supervised learning, offering a theoretical explanation for the success of feedback‑free self‑improvement and predictions about its limits.
The paper introduces a transfer learning framework paired with Conformalized Quantile Regression (CQR) to enhance solar PV power forecasting in regions with limited historical data due to load shedding. Using a source-domain dataset from Alice Springs, Australia, the model is pretrained and then adapted to simulated Bangladesh PV data with varying data availability. Experiments show that transfer learning can reduce RMSE by up to 23.7% with only one month of target data, and the combined approach achieves 94.3% empirical coverage with prediction intervals 14% narrower than without transfer learning.
The paper introduces Wasserstein‑Tilted Flow Maps (WTF), a simulation‑free reinforcement learning method that fine‑tunes pre‑trained flow‑based generative models by adding an optimal transport regularizer derived from the model’s drift. Unlike traditional KL‑reward tilting, WTF transports individual samples toward higher reward, framing the problem as a deterministic optimal control task on the flow map. Experiments on ImageNet‑256 and text‑to‑image demonstrate that WTF achieves higher reward and comparable or better diversity while reducing training compute by up to 280×.
The paper introduces ZO-COSMO, an index‑free one‑hop mixing scheme for decentralized zeroth‑order optimization that couples two‑query estimation with average‑preserving masked consensus. It characterizes the necessary one‑hop condition for sparse communication, derives sharp contraction bounds and convergence guarantees for core and sparse‑momentum updates, and demonstrates empirical gains on synthetic agents and Qwen LoRA workers, achieving notable accuracy improvements over traditional Rand‑k and all‑neighbor mixing methods.
The paper introduces LLMAE, a technique that transforms a pretrained decoder-only language model into a continuous text autoencoder by inserting a fixed-length latent bottleneck into its internal activations. Using a 270M Gemma 3 model with structured attention masks, LoRA adaptation, and KL regularization, LLMAE achieves near-perfect reconstruction of text sequences up to 1024 tokens. The authors further show that the resulting latent representation can be leveraged to train a latent text diffusion model for detailed image captioning, demonstrating downstream utility.
The paper introduces the Neurogenesis Network (NGN), a differentiable framework that learns the optimal number of ordered structural components in a neural network during training. By using a learnable boundary to select an active prefix of components, NGN can grow from a compact initialization and later discard unused parts. Experiments across MLPs, CNNs, GNNs, Transformers, state‑space models, LoRA, and adapters show that the learned prefixes perform comparably to fixed‑size models, demonstrating that structural capacity can be optimized directly as a count.
arXiv:2609.28434v1 Announce Type: new Abstract: Adolescent Idiopathic Scoliosis is defined as a lateral curvature of the spine that develops during adolescence, without known cause. The condition can...
arXiv:2609.27988v1 Announce Type: cross Abstract: Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direc...
arXiv:2609.27717v1 Announce Type: new Abstract: Human-written agent skills encode rich workflows for real-world problem solving, but are typically used as external inference-time instructions rather...
arXiv:2609.27284v1 Announce Type: new Abstract: We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but ac...
arXiv:2609.27333v1 Announce Type: new Abstract: Platform operators increasingly rely on system prompts and fine-tuning to govern model behavior, yet it remains unclear how reliably these intervention...
arXiv:2609.28430v1 Announce Type: new Abstract: This work addresses continuous depression-severity score prediction from clinical interview transcripts under data scarcity. We propose a sequential lo...
arXiv:2609.27022v1 Announce Type: new Abstract: In this paper, we investigate the impact of adversarial attacks on identity encoders within a realistic de-identification framework. Our experiments sh...