LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2608. 13597v1 Announce Type: cross Abstract: Coverless image steganography (CIS) synthesizes a stego image rather than modifying an existing cover image, enabling authorized recipients to reconstruct the original secret image from the stego.
arXiv:2608. 14456v1 Announce Type: new Abstract: Short-horizon forecasting of fine particulate matter (PM2.
arXiv:2608. 14264v1 Announce Type: cross Abstract: Model merging combines trained models directly in weight space, offering a compute-efficient alternative to additional fine-tuning.
We introduce ReRef-3D, a benchmark for language-guided placement in 3D scenes. It contains 33,826 instructions across 998 CLEVR-derived scenes, spanning 16 placement families and direct, one-hop, and two-hop references.
A learning system can occupy execution states that are indistinguishable under every declared present-behavior readout yet respond differently to future training. We formalize this through fiber fingerprints: controlled future-learning response laws restricted to present-behavior equivalence classes.
Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of large language models, but its factorized parameterization creates a tension between accurate aggregation of local updates and con...
Bangla-English tutoring requires more than producing a correct translation: learners also need explanations of grammar differences, awareness of their likely errors, and targeted practice. We present...
Subject-driven image personalization---generating new images that preserve the identity of one or several reference subjects in novel scenes---is a foundational capability for modern visual content creation. It is currently dominated by generalized methods that fine-tune a pretrained multimodal diffusion transformer (MMDiT) on hundreds of thousands to millions of paired \emph{(reference, composed-target)} examples, where each composed target is a synthesized image of the subject in a novel scene.
Recent advances in large language models (LLMs) have reshaped semantic analysis. Opinion Extraction (OE) for Science and Technology Intelligence (STI) requires concise core opinions from large information streams.
Smart manufacturing processes are often installed with a large number of sensors, imaging devices and computers, which not only enable instant communication across various modules of a production syst...
arXiv:2608. 13250v1 Announce Type: cross Abstract: Normative datasets are often used to train and align AI systems, but the norms they contain can function as action-guiding patterns rather than neutral moral knowledge.
arXiv:2608. 12374v1 Announce Type: cross Abstract: Language models (LMs) struggle with logical tasks like reasoning on syllogisms.
arXiv:2608. 13344v1 Announce Type: new Abstract: Long-horizon Earth observation reasoning requires models to organize multi-stage geographic evolution, localize spatial changes, detect temporal anomalies, and infer future from extended image sequences.
arXiv:2601. 21628v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy and copyright.
arXiv:2606. 07316v2 Announce Type: replace-cross Abstract: Can a committee of LLM agents reach agreement that is certifiable at the level of meaning, not only at the level of a label?
arXiv:2608. 12845v1 Announce Type: cross Abstract: Semantic ID (SID)-based generative recommendation has recently achieved remarkable success.
arXiv:2608. 13495v1 Announce Type: cross Abstract: Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, model development, and safety analysis.
arXiv:2608. 12795v1 Announce Type: cross Abstract: Simulating the ALICE Zero Degree Calorimeter (ZDC) neutron detector responses at the LHC is computationally expensive, requiring complex Monte Carlo chains.
arXiv:2608. 13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants.
arXiv:2506. 17337v5 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown promise in automating image diagnosis and interpretation in clinical settings.