Large Language Models (LLMs) are rapidly being adopted by users across the globe, who interact with them in a diverse range of languages. At the same time, there are well-documented imbalances in the training data and optimisation objectives of this technology, raising doubts as to whether LLMs can represent the cultural diversity of their broad user base. In this study, we look at LLMs and cultural values and examine how prompt language and cultural framing influence model responses and their alignment with human values in different countries. We probe 10 LLMs with 63 items from the Hofstede Values Survey Module and World Values Survey, translated into 11 languages, and formulated as prompts with and without different explicit cultural perspectives. Our study confirms that both prompt language and cultural perspective produce variation in LLM outputs, but with an important caveat: While targeted prompting can, to a certain extent, steer LLM responses in the direction of the predominant values of the corresponding countries, it does not overcome the models' systematic bias toward the values associated with a restricted set of countries in our dataset: the Netherlands, Germany, the US, and Japan. All tested models, regardless of their origin, exhibit remarkably similar patterns: They produce fairly neutral responses on most topics, with selective progressive stances on issues such as social tolerance. Alignment with cultural values of human respondents is improved more with an explicit cultural perspective than with a targeted prompt language. Unexpectedly, combining both approaches is no more effective than cultural framing with an English prompt. These findings reveal that LLMs occupy an uncomfortable middle ground: They are responsive enough to changes in prompts to produce variation, but too firmly anchored to specific cultural defaults to adequately represent cultural diversity.

The Generic Viewpoint Assumption (GVA) states that the position of the viewer or the light in a scene is not special. Thus, any estimated parameters from an observation should be stable under small perturbations such as object, viewpoint or light positions. The GVA has been analyzed and quantified in previous works, but has not been put to practical use in actual vision tasks. In this paper, we show how to utilize the GVA to estimate shape and illumination from a single shading image, without the use of other priors. We propose a novel linearized Spherical Harmonics (SH) shading model which enables us to obtain a computationally efficient form of the GVA term. Together with a data term, we build a model whose unknowns are shape and SH illumination. The model parameters are estimated using the Alternating Direction Method of Multipliers embedded in a multi-scale estimation framework. In this prior-free framework, we obtain competitive shape and illumination estimation results under a variety of models and lighting conditions, requiring fewer assumptions than competing methods.

The Generic Viewpoint Assumption (GVA) states that the position of the viewer or the light in a scene is not special. Thus, any estimated parameters from an observation should be stable under small perturbations such as object, viewpoint or light positions. The GVA has been analyzed and quantified in previous works, but has not been put to practical use in actual vision tasks. In this paper, we show how to utilize the GVA to estimate shape and illumination from a single shading image, without the use of other priors. We propose a novel linearized Spherical Harmonics (SH) shading model which enables us to obtain a computationally efficient form of the GVA term.

The paper presents an interesting approach on the intrinsic image decomposition problem: given an input rgb image, it decomposes it first into shape (normals), reflectance (albedo) and illumination (point light) using an encoder-decoder deep architecture with 3 outputs. Then there is another encoder-decoder that takes the predicted normals and light and outputs the shading of the shape. Finally, the result comes from a multiplication between the estimated reflectance (from the 1st encoder-decoder) with the estimated shading. The idea of having a reconstruction loss to recover the input image is interesting, but I believe that is only partially employed in the paper. The network architecture still needs labeled data for the initial training.

The Generic Viewpoint Assumption (GVA) states that the position of the viewer or the light in a scene is not special. Thus, any estimated parameters from an observation should be stable under small perturbations such as object, viewpoint or light positions. The GVA has been analyzed and quantified in previous works, but has not been put to practical use in actual vision tasks. In this paper, we show how to utilize the GVA to estimate shape and illumination from a single shading image, without the use of other priors. We propose a novel linearized Spherical Harmonics (SH) shading model which enables us to obtain a computationally efficient form of the GVA term.

Interval temporal logics (ITLs) are logics for reasoning about temporal statements expressed over intervals, i.e., periods of time. The most famous ITL studied so far is Halpern and Shoham's HS, which is the logic of the thirteen Allen's interval relations. Unfortunately, HS and most of its fragments have an undecidable satisfiability problem. This discouraged the research in this area until recently, when a number non-trivial decidable ITLs have been discovered. This paper is a contribution towards the complete classification of all different fragments of HS. We consider different combinations of the interval relations Begins, After, Later and their inverses Abar, Bbar, and Lbar. We know from previous works that the combination ABBbarAbar is decidable only when finite domains are considered (and undecidable elsewhere), and that ABBbar is decidable over the natural numbers. We extend these results by showing that decidability of ABBar can be further extended to capture the language ABBbarLbar, which lays in between ABBar and ABBbarAbar, and that turns out to be maximal w.r.t decidability over strongly discrete linear orders (e.g. finite orders, the naturals, the integers). We also prove that the proposed decision procedure is optimal with respect to the complexity class.