Tail-Weight Control and Localized Generalization in Nearly Low-Rank Adversarial Classification
arXiv:2609.23688v3 Announce Type: replace-cross Abstract: Empirical ramp fitting can assign weight to pure-noise features even when the population optimum ignores…
KUPAS MASTER: Distilling the Tacit Expertise of Master Practitioners into Agent-Ready Experience Corpora
arXiv:2609.37673v1 Announce Type: new Abstract: Experienced professionals know more than just facts and conclusions. They know which cues matter, why…
Beyond Forecasting: Recasting Volatility Control as a Routing Problem
arXiv:2608.10375v2 Announce Type: replace-cross Abstract: Volatility control converts risk estimates into portfolio exposure, yet existing approaches often rely on a…
VLANeXt Family: A Systematic Study of VLA Models from Core Recipes to Emerging Paradigms
arXiv:2602.18532v5 Announce Type: replace-cross Abstract: Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, leveraging strong visual and…
The Linear Representation Hypothesis for Vision-Language-Action Models
arXiv:2609.30996v1 Announce Type: cross Abstract: The linear representation hypothesis (LRH) has become a standard lens for measuring and intervening on…
Accounting for Bias Enables Sustainable LLM Evaluation
arXiv:2609.31184v1 Announce Type: new Abstract: LLM-as-a-judge has become the de facto standard for scalable, subjective evaluation, yet current leaderboards compensate…
AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side
arXiv:2609.31166v1 Announce Type: cross Abstract: Recommender systems have traditionally been developed for platforms. However, this has given rise to many…
Improving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting
arXiv:2609.31169v1 Announce Type: cross Abstract: Multimodal Machine Translation aims to incorporate additional signal from non-textual modalities to improve translations by…
ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts
arXiv:2609.29349v2 Announce Type: replace-cross Abstract: ArGuard is a shared task on harmful content detection in Arabic memes and LLM prompts.…
FLIP: Final Layer Inference-Time Probing for Vision-Language Models
arXiv:2609.30993v1 Announce Type: cross Abstract: We present FLIP, a final-layer inference-time probe for testing whether a logit-facing intervention site in…