arXiv:2601.10936v1 Announce Type: new Abstract: Exploratory searches are characterized by under-specified goals and evolving query intents. In such scenarios, retrieval models that can capture user-specified nuances in query intent and adapt results accordingly are desirable — instruction-following retrieval models promise such a capability. In this work, we evaluate instructed retrievers for the prevalent yet under-explored application of aspect-conditional seed-guided exploration using an expert-annotated test collection. We evaluate both recent LLMs fine-tuned for instructed retrieval and general-purpose LLMs prompted […]

Ver mais

arXiv:2602.09229v1 Announce Type: new Abstract: Cosine similarity is prevalent in contrastive learning, yet it makes an implicit assumption: embedding magnitude is noise. Prior work occasionally found dot product and cosine similarity comparable, but left unanswered WHAT information magnitude carries, WHEN it helps, and HOW to leverage it. We conduct a systematic study through a $2 times 2$ ablation that independently controls input-side and output-side normalization across text and vision models. Our findings reveal three key insights. First, in […]

Ver mais

arXiv:2601.15308v1 Announce Type: new Abstract: Extended Reality (XR), including virtual, augmented, and mixed reality, provides immersive and interactive experiences across diverse applications, from VR-based education to AR-based assistance and MR-based training. However, widespread XR adoption remains limited due to two key challenges: 1) the high cost and complexity of authoring 3D content, especially for large-scale environments or complex interactions; and 2) the steep learning curve associated with non-intuitive interaction methods like handheld controllers or scripted gestures. Generative AI […]

Ver mais

arXiv:2601.05401v1 Announce Type: new Abstract: As an emergent process, creativity relies on explorations via sampling and prototyping for problem construction. These activities compile knowledge, provide a context enveloping the solution, and answer questions. With Generative AI, practitioners can go beyond sampling existing media towards instantly generating and remixing new ones. We refer to this convergence as ‘protosampling’. Using existing literature we ground a definition for protosampling and operationalize it through Atelier, a canvas-like system that leverages a variety […]

Ver mais

Catastrophic forgetting is a major problem in continual learning, and lots of approaches arise to reduce it. However, most of them are evaluated through task accuracy, which ignores the internal model structure. Recent research suggests that structural collapse leads to loss of plasticity, as evidenced by changes in effective rank (eRank). This indicates a link to forgetting, since the networks lose the ability to expand their feature space to learn new tasks, which forces the network to overwrite […]

Ver mais

We propose a new method for a non-parametric estimation of Renyi and Shannon information for a multivariate distribution using a corresponding copula, a multivariate distribution over normalized ranks of the data. As the information of the distribution is the same as the negative entropy of its copula, our method estimates this information by solving a Euclidean graph optimization problem on the empirical estimate of the distribution’s copula. Owing to the properties of the copula, we show that the […]

Ver mais

arXiv:2601.20498v1 Announce Type: cross Abstract: Diffusion models provide a principled framework for generative modeling via stochastic differential equations and time-reversed dynamics. Extending spectral diffusion approaches to spherical data, however, raises nontrivial geometric and stochastic issues that are absent in the Euclidean setting. In this work, we develop a diffusion modeling framework defined directly on finite-dimensional spherical harmonic representations of real-valued functions on the sphere. We show that the spherical discrete Fourier transform maps spatial Brownian motion to a […]

Ver mais

“Speed” in data engineering is a trade-off, not a single metric. To build effective systems, you must distinguish between two competing concepts: – Data Latency (Freshness): How long it takes for an event to reach your report. – Query Latency (Responsiveness): How long a user waits for a dashboard to load. The Conflict: Optimizing for real-time freshness often slows down query performance because the system can’t pre-calculate data. Conversely, pre-calculating data for “snappy” dashboards usually requires batching, which […]

Ver mais

arXiv:2602.13226v1 Announce Type: new Abstract: Detecting text generated by large language models (LLMs) is crucial but challenging. Existing detectors depend on impractical assumptions, such as white-box settings, or solely rely on text-level features, leading to imprecise detection ability. In this paper, we propose a simple but effective and practical LLM-generated text detection method, VaryBalance. The core of VaryBalance is that, compared to LLM-generated texts, there is a greater difference between human texts and their rewritten version via LLMs. […]

Ver mais