arXiv:2605.14749v1 Announce Type: cross Abstract: Intervention is one of the most representative and widely used methods for understanding the internal representations of large language models (LLMs). However, existing intervention methods are confined to linear interventions grounded in the Linear Representation…
arXiv:2605.13999v1 Announce Type: new Abstract: Discrete diffusion models are increasingly competitive for language modeling, yet it remains unclear how their denoising objectives organize learning. Although these objectives target the full data distribution, we show that the exact reverse process induces…
arXiv:2605.14995v1 Announce Type: cross Abstract: Every day, users generate digital traces (e.g., social media posts, chats, and online interactions) that are inherently timestamped and may reflect aspects of their mental state. These traces can be organized into temporal trajectories that…
arXiv:2605.14014v1 Announce Type: new Abstract: Internet of Things (IoT) systems continuously collect heterogeneous sensing signals from ubiquitous sensors to support intelligent applications such as human activity analysis, emotion monitoring, and environmental perception. These signals are inherently non-stationary and multi-scale, posing…
arXiv:2502.00270v3 Announce Type: replace Abstract: The performance of an LLM depends heavily on the relevance of its training data to the downstream evaluation task. However, in practice, the data involved in an unseen evaluation task is often unknown (e.g., conversations…
arXiv:2605.14026v1 Announce Type: new Abstract: For reinforcement learning in data-scarce domains like real-world robotics, intensive data reuse enhances efficiency but induces overfitting. While prior works focus on critic bias, representation-level instability in Self-Predictive Learning (SPL) under high Update-to-Data (UTD) regimes…
arXiv:2509.25826v3 Announce Type: replace Abstract: Inherent temporal heterogeneity, such as varying sampling densities and periodic structures, has posed substantial challenges in zero-shot generalization for Time Series Foundation Models (TSFMs). Existing TSFMs predominantly rely on massive parameterization to absorb such heterogeneity,…
arXiv:2605.14037v1 Announce Type: new Abstract: Under modern test-time compute and agentic paradigms, language models process ever-longer sequences. Efficient text generation with transformer architectures is increasingly constrained by the Key-Value cache memory footprint and bandwidth. To address this limitation, we introduce…
arXiv:2512.02920v3 Announce Type: replace Abstract: We consider analyzing traffic accident patterns using both road network data and satellite images aligned to road graph nodes. Previous work for predicting accident occurrences relies primarily on road network structural features while overlooking physical…
arXiv:2605.14063v1 Announce Type: new Abstract: Continual test-time adaptation (CTTA) updates a pretrained model online on an unlabeled, non-stationary stream while anchoring it to a frozen source checkpoint. This anchor is useful only when the source remains reliable. On CCC-Hard, however,…
