arXiv:2605.04723v1 Announce Type: cross Abstract: Attribute-aware sequential recommendation entails predicting the next item a user will interact with based on a chronologically ordered history of past interactions, enriched with item attributes. Existing methods typically leverage self-attention mechanisms to aggregate the…
arXiv:2605.05049v1 Announce Type: cross Abstract: Frontier models increasingly adopt Mixture-of-Experts (MoE) architectures to achieve large-model performance at reduced cost. However, training MoE models on HPC platforms is hindered by large memory footprints, frequent large-scale communication across heterogeneous networks, and severe…
arXiv:2605.04209v1 Announce Type: cross Abstract: We present Sparse Backdoor, a supply-chain attack that plants a emph{provably undetectable} backdoor in pre-trained image classifiers, including convolutional networks and Vision Transformers. The attack injects a structured sparse perturbation along a randomly chosen direction…
arXiv:2605.04504v1 Announce Type: cross Abstract: Existing prompt learning for VLMs exhibits a modality asymmetry, predominantly optimizing text tokens while still relying on frozen visual encoder as holistic extractor and neglecting the spectral granularity essential for fine-grained discrimination. To bridge this,…
arXiv:2605.02356v2 Announce Type: replace Abstract: We introduce the Z-Domain Neural Operator (ZNO), a causal neural operator whose layers are stable low-rank multiple-input multiple-output (MIMO) rational filters parameterized directly in the $z$-plane. ZNO addresses a limitation of existing operator learning methods,…
arXiv:2602.10144v2 Announce Type: replace-cross Abstract: Minimizing the inference cost and latency of foundation models has become a crucial area of research. Optimization approaches include theoretically lossless methods and others without accuracy guarantees like quantization. In all of these cases it…
arXiv:2605.04061v1 Announce Type: new Abstract: Understanding how large language models encode task identity from few-shot demonstrations is a central open problem in mechanistic interpretability. Prior work uses linear probing to localize task representations, reporting high classification accuracy at specific layers.…
arXiv:2602.09130v4 Announce Type: replace Abstract: Model compression is increasingly essential for deploying large language models (LLMs), yet existing comparative studies largely focus on pruning and quantization evaluated primarily on knowledge-centric benchmarks. Thus, we introduce UniComp, a unified evaluation framework for…
arXiv:2605.04059v1 Announce Type: new Abstract: Deep learning models continue to scale, with some requiring more storage than many large-scale datasets. Thus, we introduce a new paradigm: Continual Distillation (CD), where a student learns sequentially from a stream of teacher models…
arXiv:2605.04060v1 Announce Type: new Abstract: Recently, a new paradigm named emph{drifting model} has been proposed for mapping distributions, which achieves the SOTA image generation performance over ImageNet via one-step neural functional evaluation (NFE). The basic idea is to compute a…
