LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2609.39679v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) must remain effective when new spoofing attacks emerge after deployment. Emerging audio language model (ALM)-based ADD...
arXiv:2406.02447v5 Announce Type: replace Abstract: Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safegua...
arXiv:2605.07938v2 Announce Type: replace Abstract: Single-cell representation learning (SCRL) from gene expression data offers a way to uncover the complex regulatory logic underlying cellular funct...
arXiv:2610.00994v1 Announce Type: new Abstract: Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce V...
arXiv:2610.01098v1 Announce Type: new Abstract: Illusory matches between distinct yet visually similar 3D surfaces--doppelgangers--remain a fundamental obstacle for large-scale, in-the-wild 3D recons...
arXiv:2610.01215v1 Announce Type: new Abstract: GUI agents require high-quality interaction trajectories to learn how software environments respond to actions, maintain state, and support multi-step...
arXiv:2610.01229v1 Announce Type: new Abstract: A compact dynamic-scene representation must retain both the surfaces seen over time and the appearance needed to render them from new viewpoints. We pr...
arXiv:2404.17569v4 Announce Type: replace Abstract: This paper aims to generate materials for 3D meshes from text descriptions. Unlike existing methods that synthesize texture maps, we propose to gen...
PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning explores how to maintain a model’s existing abilities while teaching it new ones through supervised fine‑tuning on offline agent trajectories. The authors compare standard SFT, KL‑penalty, and update‑magnitude constraints, finding that these methods still degrade non‑target capabilities. They introduce Privilege‑Guided SFT (PG‑SFT), which uses turn‑level information gain to modulate supervision strength, achieving a better trade‑off between acquiring new skills and preserving existing ones, though with a slight drop in target‑task performance.
The paper introduces component routing for self‑improving GUI agents, separating experience into locators, procedures, state facts, and lessons, and directing each to either the model weights or the prompt context. Experiments across three backbone families, two environments, and multiple seeds show that routing improves performance over whole‑trajectory baselines, with a rule based on recurrence and state‑conditionality accurately predicting the optimal destination. The study also analyzes how training dynamics and producer‑consumer differences affect the value of each destination, revealing that readout decreases for frequently recurring items when written to weights, while context gains grow with the information gap and weight gains shrink with the policy gap.
The paper examines the performance of evolutionary transfer learning and TD(lambda) in the three‑dimensional chess game Dragonchess. By re‑implementing the engine in C++ to accelerate play, the authors ran 10,000 games with statistical confidence, showing both adaptive methods outperform all other agents in a round‑robin tournament. The results indicate no significant performance difference between the evolved and learned evaluation functions, demonstrating the effectiveness of adaptive techniques in complex, novel game domains.
arXiv:2610.00405v1 Announce Type: cross Abstract: Time-series foundation models (TSFMs) perform strongly across forecasting tasks, but their per-series inference is ill-suited to neighbor-rich foreca...
arXiv:2610.00604v1 Announce Type: cross Abstract: Vision-language-action policies often see only one or a few recent frames, which makes it difficult to evaluate how they use information that disappe...
arXiv:2610.00767v1 Announce Type: cross Abstract: Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later trai...
arXiv:2610.00814v1 Announce Type: cross Abstract: Synthetic data are increasingly used to scale LLM training, yet more synthetic data do not necessarily produce better models. Useful synthetic data m...
arXiv:2610.01143v1 Announce Type: cross Abstract: Despite strong mean accuracy, tabular foundation models (TFMs) can perform poorly on underrepresented groups under subpopulation shift, where group p...
arXiv:2610.02015v1 Announce Type: cross Abstract: Recent advances in LLM reasoning models---driven primarily by the paradigm of post-training via reinforcement learning with verifiable reward (RLVR)-...
arXiv:2610.02186v1 Announce Type: cross Abstract: Molecular learning models are strongly shaped by their underlying representations. Yet standard sequential and graph formalisms struggle to explicitl...
arXiv:2610.00571v1 Announce Type: cross Abstract: Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical problems, but often produce lengthy, repetitive,...
The paper introduces a method to purify LoRA-tuned large language models (LLMs) against backdoor attacks without relying on trigger knowledge, clean references, or retraining. By extracting high‑fidelity backdoor directions and projecting LoRA updates onto orthogonal null spaces in input and output channels, the approach reduces attack success rates from nearly 100% to under 10%. Experiments demonstrate that this null‑space projection preserves both the base model’s general capabilities and the new downstream skills learned through the adapter across various tasks.