arXiv:2601.15385v1 Announce Type: new Abstract: Natural-language-to-visualization (NL2VIS) systems based on large language models (LLMs) have substantially improved the accessibility of data visualization. However, their further adoption is hindered by two coupled challenges: (i) the absence of standardized evaluation metrics makes it difficult to assess progress in the field and compare different approaches; and (ii) natural language descriptions are inherently underspecified, so multiple visualizations may be valid for the same query. To address these issues, we introduce VegaChat, a […]

Ver mais

Machine unlearning enables models to selectively forget training data, driven by privacy regulations such as GDPR and CCPA. However, its fairness implications remain underexplored: when a model forgets a demographic group, does it neutralize that concept or redistribute it to correlated groups, potentially amplifying bias? We investigate this bias redistribution phenomenon on CelebA using CLIP models (ViT/B-32, ViT-L/14, ViT-B/16) under a zero-shot classification setting across intersectional groups defined by age and gender. We evaluate three unlearning methods, Prompt […]

Ver mais

arXiv:2602.16832v1 Announce Type: new Abstract: Safety alignment of large language models (LLMs) is mostly evaluated in English and contract-bound, leaving multilingual vulnerabilities understudied. We introduce textbf{Indic Jailbreak Robustness (IJR)}, a judge-free benchmark for adversarial safety across 12 Indic and South Asian languages (2.1 Billion speakers), covering 45216 prompts in JSON (contract-bound) and Free (naturalistic) tracks. IJR reveals three patterns. (1) Contracts inflate refusals but do not stop jailbreaks: in JSON, LLaMA and Sarvam exceed 0.92 JSR, and in […]

Ver mais

arXiv:2511.03369v3 Announce Type: replace-cross Abstract: Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause significant harm. However, evaluating the fairness of models is a complex challenge, and approaches that do so typically utilize standard question-answer (QA) styled schemes. Such methods often overlook deeper issues by interpreting the model’s refusal responses as positive fairness measurements, which creates a false sense of fairness. In this work, we […]

Ver mais

arXiv:2607.00001v1 Announce Type: new Abstract: Most approaches to AI alignment treat human preferences as fixed targets to be inferred and optimized. This assumption conflicts with extensive empirical evidence showing that preferences are layered, dynamic, and constructed through interaction–particularly with adaptive technologies. As AI systems become more persistent, personalized, and socially embedded, they increasingly participate in shaping what people attend to, value, and endorse over time. We introduce Constructive Alignment, a paradigm that reframes alignment as a control problem […]

Ver mais

arXiv:2601.16250v2 Announce Type: replace Abstract: We study a general framework of distributional computational graphs: computational graphs whose inputs are probability distributions rather than point values. We analyze the discretization error that arises when these graphs are evaluated using finite approximations of continuous probability distributions. Such an approximation might be the result of representing a continuous real-valued distribution using a discrete representation or from constructing an empirical distribution from samples (or might be the output of another distributional computational […]

Ver mais

arXiv:2604.02387v1 Announce Type: new Abstract: Precision reducers are critical components in robotic systems, directly affecting the motion accuracy and dynamic performance of humanoid robots, quadruped robots, collaborative robots, industrial robots, and SCARA robots. This paper presents a dynamic toolkit for analyzing the transmission characteristics of precision reducers with explicit contact geometry. A unified framework is proposed to address the challenges in modeling accurate contact behaviors, evaluating gear stiffness, and predicting system vibrations. By integrating advanced contact theories and […]

Ver mais