Knowledge catalogue
When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How much tree-structured compositional content survive
arXiv:2609.34343v1 Announce Type: new Abstract: Dataset distillation compresses a training set into a small synthetic set, usually evaluated one at a time. In federated and data-governance settings, s
arXiv:2603.19198v2 Announce Type: replace-cross Abstract: We introduce the exponentially weighted signature (EWS), a continuous-time model that computes iterated integrals of a path, where each increm
arXiv:2609.32759v1 Announce Type: new Abstract: We introduce the Extender, a log-structured variant of the standard Transformer architecture. In a standard Transformer, each layer communicates with su
arXiv:2609.35392v1 Announce Type: new Abstract: Adam is the default optimizer for training modern deep neural networks, yet its adaptive behavior remains poorly understood due to the complex interacti
arXiv:2609.32934v1 Announce Type: new Abstract: Neural network training is inherently stochastic, with factors such as weight initialization leading to distinct models despite comparable predictive pe
arXiv:2609.32196v1 Announce Type: cross Abstract: Language models are now routinely graded by other language models. If post-training makes a model's own writing more predictable, it may also teach th
arXiv:2609.32942v1 Announce Type: cross Abstract: A two-hop question makes a language model retrieve twice: once to produce a bridge entity, and once to retrieve with it. Transformers resolve that ent
arXiv:2609.33078v1 Announce Type: new Abstract: Automatic differentiation (AD) lets neural networks compute derivatives of governing equations to machine precision, and this precision has made it the
arXiv:2609.33240v1 Announce Type: new Abstract: The Forward-Forward Algorithm (FFA) replaces backpropagation (BP) with layer-wise local contrastive objectives, eliminating the backward pass and the ne
arXiv:2609.33597v1 Announce Type: cross Abstract: Side-channel evaluators routinely inspect leakage tests while acquisition is still running, and extend or stop the campaign based on what they see. Fi
arXiv:2609.34050v1 Announce Type: cross Abstract: What determines the unavoidable sample cost of learning cyclic causal structure? For cyclic linear non-Gaussian models, we study exact condensation re
arXiv:2607.14246v2 Announce Type: replace-cross Abstract: Generative models are steered with knobs -- prompts, guidance scales, property tags. Turn one as hard as you like and, past a point, it stops
arXiv:2609.31684v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) introduces a specific failure mode in discrete diffusion language models: when retrieved context contradicts para
arXiv:2510.15508v2 Announce Type: replace Abstract: In this study, we propose an enhancement to the similarity computation mechanism in multimodal contrastive pretraining frameworks such as CLIP. Prio
arXiv:2609.34642v1 Announce Type: new Abstract: Schrodinger bridges provide an entropy-regularized framework and a principled solution for unpaired domain translation. In practice, a pretrained bridge
arXiv:2609.33376v1 Announce Type: cross Abstract: Fraud detection is an important area of research in the insurance business due to its financial implications. The primary aim of a fraud detection mod
arXiv:2609.33774v1 Announce Type: cross Abstract: Watermarking is a promising tool for establishing the provenance of AI-generated speech. While many neural audio watermarking methods rely on a separa
arXiv:2609.33688v1 Announce Type: cross Abstract: Deep learning has emerged as an efficient alternative for predicting high-performance material distributions in topology optimization. Existing method
arXiv:2609.33109v1 Announce Type: new Abstract: Grounding is a core capability of spatial vision-language models, yet most existing work focuses only on where a referred object is. Many 3D tasks also
arXiv:2606.15632v3 Announce Type: replace Abstract: Long videos challenge open-world segmentation systems to continually discover objects and preserve their identities through disappearance and reappe
arXiv:2609.35059v1 Announce Type: new Abstract: 3D anomaly detection (3DAD) aims to identify defective regions in point cloud data, serving as a critical component in industrial inspection systems. Ex
arXiv:2609.33273v1 Announce Type: new Abstract: The presence of noise that depends on the latent variables poses a fundamental challenge to identifiability. Existing results rely on conditional indepe
arXiv:2609.31682v1 Announce Type: new Abstract: More than 80 countries have reported malaria cases with 610 thousand deaths and are projected to increase. Identifying malaria early and accurately help
arXiv:2306.00206v3 Announce Type: replace Abstract: Embedding models, often obtained via self-supervised learning, extract general-purpose representations from data. Quantifying the reliability of the
arXiv:2609.33915v1 Announce Type: new Abstract: Progress in machine learning cannot outpace our ability to verify it. With an explosion in papers today, every scientific claim rests initially on trust
arXiv:2609.35649v1 Announce Type: new Abstract: Tandem mass spectrum prediction supports compound identification across metabolomics, natural-product discovery, and environmental analysis. However, pr
arXiv:2509.14025v2 Announce Type: replace Abstract: Modular Aerial Robot Systems (MARS) consist of multiple drone modules that are physically bound together to form a single structure for flight. Expl
arXiv:2609.32502v1 Announce Type: cross Abstract: De novo 3D molecular generation jointly models molecular size, topology, and geometry. Most methods pre-sample molecular size and generate Cartesian c
arXiv:2609.34697v1 Announce Type: new Abstract: We introduce Triangular Resampling (TR), a post-training method for mitigating long-horizon error accumulation in motion diffusion models. Built on Floo
arXiv:2609.32013v1 Announce Type: new Abstract: We present TriO, a multi-modal unsupervised world model that predicts 4D occupancy, obstacle segmentation, flow and LiDAR. In contrast to prior work, Tr
arXiv:2609.33419v1 Announce Type: new Abstract: Comparisons in video self-supervised learning often evaluate complete training recipes rather than isolating the method itself: architecture, objective,
arXiv:2508.02873v3 Announce Type: replace Abstract: We present the design and implementation of HASTA (Hopper with Adjustable Stiffness for Terrain Adaptation), a vertical hopping robot with real-time
arXiv:2609.32940v1 Announce Type: new Abstract: Graph convolutional networks propagate information by repeated local aggregation through a graph shift operator; i.e., a K-layer network reaches K hops
arXiv:2609.33968v1 Announce Type: cross Abstract: Testing whether two populations of networks share the same edge probabilities is a basic problem in network inference. How hard it is depends on the n
arXiv:2609.32244v1 Announce Type: new Abstract: Gait recognition always remains challenging due to severe overfitting and the rigid view constraints common in single-stage approaches. We propose a two
arXiv:2609.31998v1 Announce Type: new Abstract: Analog dial meters are widely deployed in industrial applications and utility sites, where environments and meter types vary and inspection data may be
arXiv:2609.32170v1 Announce Type: new Abstract: The performance of online reinforcement learning depends critically on design choices, especially those that affect exploration. These choices are often
arXiv:2603.16731v2 Announce Type: replace Abstract: Quantizing optimizer states is becoming an important ingredient of memory-efficient large-scale pre-training, but the resulting optimizer dynamics r
arXiv:2609.34182v1 Announce Type: new Abstract: Dexterous manipulation requires tactile feedback.However, robot tactile demonstrations are difficult to scale,because dexterous-hand teleoperation provi
arXiv:2609.35763v1 Announce Type: new Abstract: Distributional training provides collective supervision for one-step visual generation by matching real and generated features in frozen representation
arXiv:2609.35483v1 Announce Type: new Abstract: Many learning tasks map an input distribution to an output distribution. A natural way to model such an operator is to transform each input sample using
arXiv:2609.35055v1 Announce Type: new Abstract: Long contexts are central to modern transformer systems, but most expressivity results choose a different network for each fixed sequence length. We stu
arXiv:2609.32824v1 Announce Type: new Abstract: extit{Gromov-Wasserstein Distances} (GWDs) provide quantitative ways of comparing probabilistic distributions defined on different metric spaces by appl
arXiv:2602.05548v4 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), particularly GRPO, has become the standard for eliciting LLM reasoning. However, its efficien
arXiv:2609.32386v1 Announce Type: new Abstract: Impaired glucose regulation is a major contributor to metabolic dysfunction and type 2 diabetes. This study developed an interpretable machine-learning
arXiv:2609.31999v1 Announce Type: new Abstract: Whereas previous results on abilities and limitations of transformers have restricted the definition of transformers in various ways, here we study soft
arXiv:2609.35641v1 Announce Type: cross Abstract: Precise instruction following in image generation, such as satisfying object counts and spatial relations, remains an open challenge at least in part
arXiv:2609.33935v1 Announce Type: new Abstract: Adapting video models to new tasks typically requires dedicated data curation and fine-tuning. While visual analogy provides a training-free alternative
arXiv:2609.31810v1 Announce Type: cross Abstract: Video-to-music models have advanced considerably in the last few years, particularly in film and music video applications. In this paper, we investiga
arXiv:2503.10547v3 Announce Type: replace Abstract: Concept-based explanations help users understand vision models through recognizable visual patterns. However, existing methods often rely on correla
arXiv:2609.34472v1 Announce Type: new Abstract: Acne assessment is crucial for clinical decision-making, yet traditional grading and counting are subjective and fail to account for lesion size. While
arXiv:2606.15835v2 Announce Type: replace Abstract: Diffusion models have achieved impressive empirical success in generative tasks, and their convergence theory is now relatively well understood. Mot
arXiv:2609.33030v1 Announce Type: new Abstract: World models simulate the consequences of action candidates, but good planning need not preserve every physical distinction required for accurate predic
arXiv:2609.31635v1 Announce Type: new Abstract: Clinical trajectory models are usually evaluated by next-event accuracy on observed histories. Simulation is different: models must condition on their o
arXiv:2609.33375v1 Announce Type: cross Abstract: The transition from vocoder-based to neural-codec speech synthesis makes generalization more difficult for speech deepfake detectors, particularly tho
arXiv:2609.32670v1 Announce Type: cross Abstract: When a language model explains an answer it has already given, does it reuse the computation that produced the answer or reconstruct a story from the
arXiv:2609.34091v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose dense model activations into discrete latents, making individual features easy to interpret--and easy to misinterpr
arXiv:2609.34489v1 Announce Type: new Abstract: Data pruning reduces the training cost of knowledge distillation (KD). However, the preferred teacher capacity changes with the data budget: smaller tea
arXiv:2609.34602v1 Announce Type: new Abstract: Frozen Earth-observation embeddings are judged almost entirely by spatially blocked cross-validation inside one study region. We show that this number d