Explore documented scientific discoveries, original research and new scientific developments. Search the library by topic, category or date.
arXiv:2611.03953v1 Announce Type: new Abstract: Multi-teacher on-policy distillation consolidates expert capabilities by supervising student-generated trajectories, whereas task arithmetic offers a training-free alternative through linear parameter combinations.
arXiv MLRead article →arXiv:2611.03934v1 Announce Type: new Abstract: Fast Dominance Estimation Clustering (FastDEC) is an efficient variant of Density Peak Clustering (DPC) that achieves high clustering quality through dominance-based density estimation, but remains constrained by the computational cost of exact k-nearest-neighbor (k-NN) construction and dominance component (DC) processing.
arXiv MLRead article →arXiv:2611.03928v1 Announce Type: new Abstract: Graph forecasting systems often rely on prediction intervals to quantify uncertainty across connected locations, but the true outcomes needed for evaluation may be only partially observed.
arXiv MLRead article →arXiv:2611.03916v1 Announce Type: new Abstract: Koopman representations describe nonlinear dynamics through linear evolution in a transformed space, offering an attractive framework for their linear simplicity and generality. Yet these advantages do not necessarily translate into improved performance in deep latent data assimilation (LDA).
arXiv MLRead article →arXiv:2611.03887v1 Announce Type: new Abstract: Neural controlled differential equations (Neural CDEs) evolve hidden states along continuous paths constructed by interpolating discrete observations. Sparse measurements leave the input between observation times undetermined, and admissible continuous paths consistent with the same data can produce different terminal states.
arXiv MLRead article →arXiv:2611.03876v1 Announce Type: new Abstract: Large Language Models (LLMs) often generate fluent yet incorrect responses, making un- certainty estimation important for reliable deployment. Semantic Entropy (SE) estimates uncertainty by clustering responses based on semantic equivalence, but it relies on hard entailment-based clustering.
arXiv MLRead article →arXiv:2611.03867v1 Announce Type: new Abstract: Hyperparameter optimization (HPO) returns a single optimal configuration, systematically discarding the explored performance landscape that encodes how results depend on configuration choices.
arXiv MLRead article →arXiv:2611.03862v1 Announce Type: new Abstract: Large foundation models often answer even when the available visual or textual evidence is insufficient to support a reliable conclusion. This failure to abstain makes them hard to trust in high-stakes or information-seeking settings, where a confident but unsupported answer can be worse than no answer at all.
arXiv MLRead article →arXiv:2611.03844v1 Announce Type: new Abstract: Therapeutic antibody development is often framed as comprising two discrete stages: initial discovery of novel binders followed by iterative optimization to refine these hits into therapeutic-grade molecules.
arXiv MLRead article →arXiv:2611.03768v1 Announce Type: new Abstract: Sparse attention cuts the cost of long-context inference by making the attention matrix sparse: each query attends only a subset of the sequence, chosen by a fixed pattern or, in recent production LLMs, learned per query.
arXiv MLRead article →arXiv:2611.03767v1 Announce Type: new Abstract: As general-purpose Large Language Models (LLMs), such as Gemini and DeepSeek, exhibit increasingly advanced reasoning capabilities, a critical question arises: how do their property prediction abilities compare to those of domain-specific pretrained materials models?
arXiv MLRead article →arXiv:2611.03764v1 Announce Type: new Abstract: Diffusion models trained on distinct datasets can produce highly similar samples when prompted with the same noise input, suggesting that they learn a generalized data distribution. We investigate the role of noise injected during the sampling process, and show that it plays an important role in making or breaking this strong generalization effect.
arXiv MLRead article →arXiv:2611.03756v1 Announce Type: new Abstract: Language models are typically trained with a single choice of architecture on diverse domains and data sources. Modern transformers have been extensively refined for such general-purpose learning, but are they equally effective across different subsets of the pretraining data?
arXiv MLRead article →arXiv:2611.03755v1 Announce Type: new Abstract: Financial workflows need fast, calibrated, auditable decisions, not just generated text. We train System-1 decision models, small language models fine-tuned to answer typed questions (choice/score/noul) with a probability in a single forward pass, across two model families (K2-Horizon and Qwen3.5/3.8) and nine rungs from 0.8B to 32B parameters, using one frozen LoRA…
arXiv MLRead article →arXiv:2611.03744v1 Announce Type: new Abstract: Knowledge tracing (KT) estimates learners' evolving knowledge states from interaction histories to support adaptive learning. Retrieval-augmented KT improves these estimates using cross-learner behavioral evidence, but existing approaches typically separate evidence retrieval from downstream prediction.
arXiv MLRead article →arXiv:2611.03738v1 Announce Type: new Abstract: Accurate forecasting and temporal downscaling of solar irradiance is critical for reliable renewable energy integration and grid management. Traditional methods often struggle to capture rapid irradiance variability. In this work, we develop a Transformer-based architecture for simultaneous forecasting and temporal downscaling.
arXiv MLRead article →arXiv:2611.03737v1 Announce Type: new Abstract: Extracting semantically meaningful staypoints from raw trajectory streams is a foundational prerequisite for mobility analytics. However, real-world trajectory data is frequently degraded by severe spatial noise and protracted temporal dropouts.
arXiv MLRead article →arXiv:2611.03734v1 Announce Type: new Abstract: Training a classifier means letting a validation metric decide which model is kept and when training stops. A natural requirement on that metric is superiority: every correctly classified forecast should score better than every incorrectly classified one, however close the underlying probabilities are.
arXiv MLRead article →arXiv:2611.03727v1 Announce Type: new Abstract: Benchmarks built from model hubs combine interaction data, knowledge graphs (KGs) and resource documentation, but valid files do not ensure that these artifacts describe the same objects.
arXiv MLRead article →arXiv:2611.03724v1 Announce Type: new Abstract: In receiver-directed federated learning, each site draws a trust boundary. For every source and model component it judges, on its own data, whether the transfer helps (admit), harms (reject) or cannot yet be told (abstain). We ask whether this boundary holds over hundreds of rounds.
arXiv MLRead article →arXiv:2611.03675v1 Announce Type: new Abstract: Deep neural networks extract powerful latent representations from images, enabling fast and efficient downstream analysis. However, these latent spaces lack explicit geometric structure, leading to possibly poor interpolation fidelity and misleading extrapolation.
arXiv MLRead article →arXiv:2611.03656v1 Announce Type: new Abstract: Why do some of the world's most powerful Artificial Intelligence (AI) systems still struggle to reason about cause and effect? Causal discovery, the ability to discern the underlying drivers of a system, is fundamental to scientific inquiry and has traditionally relied on structured data and statistical methods.
arXiv MLRead article →arXiv:2611.03655v1 Announce Type: new Abstract: Language models often spread a concept across many internal dimensions, making their features difficult to interpret. Sparse autoencoders (SAEs) recover clearer features after training. We ask whether models can instead learn interpretable output coordinates directly.
arXiv MLRead article →arXiv:2611.03654v1 Announce Type: new Abstract: Cardiac auscultation traditionally detects the presence of a heart murmur, but clinicians further characterize it by timing, shape, pitch, quality, and grade. Most automatic phonocardiogram analysis systems stop at binary detection and do not estimate this richer description.
arXiv MLRead article →