LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2606. 06823v1 Announce Type: cross Abstract: While deep learning has excelled in various domains, its application to sequential decision-making in finance remains challenging due to the low Signal-to-Noise Ratio (SNR) and non-stationarity of financial data.
arXiv:2510. 24561v3 Announce Type: replace-cross Abstract: LoRA has become a widely adopted method for PEFT, and its initialization methods have attracted increasing attention.
arXiv:2603. 20990v3 Announce Type: replace-cross Abstract: Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation.
arXiv:2606. 07006v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is a prevailing method for adapting large language models to reasoning tasks by imitating offline expert demonstrations, often treating a single expert trajectory as the target behavior.
arXiv:2606. 06715v1 Announce Type: cross Abstract: We ask whether topic sentiment has a causal effect on perceived political ideology, and whether the answer depends on who assigns the ideology label.
arXiv:2606. 06519v1 Announce Type: new Abstract: Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts, even when the training data is not intentionally harmful.
arXiv:2606. 07102v1 Announce Type: cross Abstract: We propose GP-Adapter, a training-free framework that augments CLIP (Contrastive Language-Image Pre-training) with Gaussian Process (GP) uncertainty modeling for few-shot classification and out-of-distribution (OOD) detection.
arXiv:2606. 07473v1 Announce Type: cross Abstract: Whisper, a widely adopted ASR model, is known to suffer from hallucinations - coherent transcriptions generated for non-speech audio entirely disconnected from the input.
arXiv:2505. 10892v2 Announce Type: replace Abstract: Post-training LLMs with RLHF and preference optimization methods (e.
arXiv:2508. 02039v2 Announce Type: replace Abstract: Increasing concerns for data privacy and other difficulties associated with retrieving source data for model training have created the need for source-free transfer learning, in which one only has access to pre-trained models instead of data from the original source domains.
arXiv:2606. 06907v1 Announce Type: cross Abstract: Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data.
arXiv:2606. 06967v1 Announce Type: new Abstract: Generative policies provide expressive and multimodal action distributions, making them attractive for reinforcement learning (RL) in complex continuous-control tasks.
arXiv:2606. 07334v1 Announce Type: cross Abstract: Harmony is a compact symbolic layer where mathematical pitch relations, acoustic consonance, and musical convention meet.
arXiv:2510. 17004v2 Announce Type: replace-cross Abstract: Purpose: To develop and evaluate a multi-agent framework (ReclAIm) for automated monitoring, detection, and correction of performance decline in medical image classification models.
arXiv:2507. 12927v2 Announce Type: replace Abstract: The general trace reconstruction problem seeks to recover an original sequence from its noisy copies independently corrupted by insertions, deletions, and substitutions.
arXiv:2605. 13268v2 Announce Type: replace-cross Abstract: Trotter Suzuki product formulas are the standard route to Hamiltonian evolution on noisy intermediate-scale quantum (\NISQ{}) hardware, but their accuracy depends on three coupled choices: term grouping, product-formula order, and time-step allocation.
arXiv:2606. 06786v1 Announce Type: new Abstract: This paper presents a forward-looking vision for integrating the emerging multi-modal multi-task federated foundation models (M3T FedFMs) into vehicular networks, with the goal of unifying the expressive power of multi-modal multi-task foundation models (M3T FMs) with the privacy-preserving and distributed learning capabilities of federated learning (FL).
arXiv:2606. 06679v1 Announce Type: cross Abstract: Court judgments are central to legal practice and jurisprudence, yet discourse analysis of Hong Kong judgments has received limited attention, owing largely to the absence of expert-annotated corpora.
arXiv:2606. 07117v1 Announce Type: cross Abstract: This paper presents Native3D, the first end-to-end 3D scene generation framework that completely bypasses 2D intermediate representations.
arXiv:2505. 05232v3 Announce Type: replace Abstract: The rapid expansion of chemistry literature poses significant challenges for researchers seeking to efficiently access domain-specific knowledge.