LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2609.09551v1 Announce Type: cross Abstract: Recommender systems have become core infrastructure for modern online platforms, personalizing content at scale and strongly influencing what users s...
arXiv:2609.09735v1 Announce Type: cross Abstract: Healthcare systems, mental health, and public well-being are increasingly affected by cyberbullying and harmful online interactions. This paper prese...
arXiv:2604.23036v2 Announce Type: replace-cross Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layer...
arXiv:2609.06289v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerged as a lightweight, inferenc...
arXiv:2609.10311v1 Announce Type: cross Abstract: The lottery ticket hypothesis posits the existence of winning tickets: sparse subnetworks that, when trained in isolation from their original initial...
SwiftExplorer is a training‑free diffusion model alignment plugin that addresses two key issues in objective‑guided sampling: the loss of diversity due to strong directional bias and the inefficiency of constant guidance. It introduces an Inheritance‑Restart exploration mechanism to prevent early convergence and enhance the likelihood of high‑reward trajectories, while a Quality‑Efficiency arbitration mechanism removes incorrect signals and dynamically stops generation when optimal reward gain is achieved. Experiments show that SwiftExplorer improves preference, fidelity, diversity, and richness across multiple evaluation metrics.
arXiv:2503.13938v3 Announce Type: replace-cross Abstract: Comprehensive traffic scene understanding is a foundational capability for Intelligent Transportation Systems (ITS) underpinning applications...
arXiv:2605.18163v2 Announce Type: replace Abstract: Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor...
MemCorr-DP is a diffusion policy that uses counterfactual correspondence conditioning to align a frozen RoMa v2 reference trajectory with the current scene in explicit 3D relations. By assigning opposite behaviors the same physical state and noisy action while retaining reference-specific denoising targets, and then fine‑tuning with mixed‑condition data, the policy learns to adapt from ground‑truth geometry to measured correspondence errors. In a door‑opening task with large spatial and viewpoint shifts, MemCorr‑DP achieves 96.67% closed‑loop success versus 88.00% for a visual Transformer, demonstrating that explicit 3D reference relations provide robust conditioning when spatial and viewpoint changes are compounded.
arXiv:2609.07726v1 Announce Type: cross Abstract: Automatic modulation classification (AMC) models are frequently trained and validated on synthetic or channel-cabled data, leaving open the question...
The paper introduces SALT, a lightweight post‑training technique that injects span‑level supervision into existing cross‑lingual sentence encoders to enhance token representations. Evaluated on five multilingual token‑level benchmarks, SALT achieves the best overall results on four tasks, surpassing alternative fine‑tuning methods and competitive encoders. Additionally, SALT improves sentence‑level performance on cross‑lingual retrieval and classification tasks, demonstrating the effectiveness of span‑level supervision for both token and sentence representations.
The study investigates how the composition of data during the mid‑training phase of language models affects performance across multiple domains. Experiments with Qwen3‑8B‑Base on five distinct KOR‑Bench domains show that moderate coverage (10%‑40%) yields the best per‑domain results, and that alignment passes cannot fully close the performance gaps created by mid‑training data choices. Additionally, zero coverage in mid‑training severely degrades accuracy, while a carefully tuned allocation can provide the largest overall pipeline improvement.
arXiv:2609.09757v1 Announce Type: cross Abstract: Real-time MRI (rtMRI) captures the dynamics of the entire vocal tract during speech, but labeled data are scarce and the modality - single-slice, gra...
arXiv:2609.08966v1 Announce Type: new Abstract: Language-model checkpoints are commonly selected by pretraining loss or benchmark scores, assuming that the highest-scoring checkpoint will remain the...
The paper introduces BROT, a two‑step approach for estimating optimal transport maps. First, it computes the unregularized OT plan, then fits a deep neural network to the resulting barycentric targets using least‑squares regression. The authors prove that, under standard regularity conditions, BROT achieves the minimax convergence rate when the true OT map is Lipschitz, and demonstrate its effectiveness on synthetic data, images, and downstream tasks such as single‑cell perturbation prediction and unsupervised domain adaptation.
arXiv:2609.06806v1 Announce Type: new Abstract: Training strategy, namely whether to retrain from scratch or fine-tune from the previous checkpoint, is an overlooked decision variable in active learn...
Shortcut learning occurs when classifiers rely on spurious correlations instead of true diagnostic features. The authors argue that this is essentially a calibration issue: unconstrained training aligns shortcut groups with their prevalence, causing over‑confidence in one group and under‑confidence in another. They introduce two encoder‑agnostic methods—a regularizer and a post‑hoc recalibration—to equalize prevalence across shortcut groups, achieving significant performance gains on chest‑drain‑pneumothorax benchmarks with both fine‑tuned CNNs and frozen foundation‑model backbones.
TamilEOT is a new dataset and two audio‑only models for detecting semantic end‑of‑turn in Tamil telephone speech, comprising 18,485 labeled turn boundaries from 116 real conversations. The models, fine‑tuned from Smart Turn v3, achieve 83.71% and 86.13% accuracy on a held‑out set, with ROC‑AUC rising from 0.751 to 0.921, and run in under 150 ms on a laptop CPU. The paper also reports the cost of building the dataset, the accuracy of rule‑derived labels versus human agreement, and the impact of encoder capacity on performance. whyItMatters":"The study provides the first publicly available Tamil end‑of‑turn detection resource, enabling more accurate voice agents for South Indian languages and demonstrating efficient, low‑latency models that outperform zero‑shot baselines."
arXiv:2609.07666v1 Announce Type: new Abstract: Full-parameter fine-tuning of large language models has substantial memory costs because backpropagation stores activations and gradients. Zeroth-order...
arXiv:2609.06670v1 Announce Type: new Abstract: The In-context learning (ICL) paradigm aids large language models (LLMs) to adapt to new tasks without need for fine-tuning. However, selecting an opti...