Knowledge catalogue
arXiv:2610.20850v1 Announce Type: new Abstract: Architectural biases restrict the class of functions that a diffusion score network can represent, but their effect on generalization remains poorly und
arXiv:2610.22258v1 Announce Type: cross Abstract: The human brain effortlessly deciphers colors and textures from visual stimuli and reconstructs the world around us, yet preserving such details remai
arXiv:2610.22325v1 Announce Type: new Abstract: Reconstructing human motion in 4D requires identifying the same surface points through articulation, deformation and changes in visibility. We introduce
arXiv:2610.22330v1 Announce Type: new Abstract: Continuous diffusion language models (CDLMs) offer an alternative approach to parallel language generation; however, most existing studies directly use
arXiv:2610.21639v1 Announce Type: new Abstract: Ensemble weather forecasts can look reliable in global averages while hiding too little spread in some cases and too much in others. These errors vary a
arXiv:2610.21672v1 Announce Type: cross Abstract: Diffusion language models generate text by reversing a classical diffusion process over token sequences. We show that their continuous-time forward an
arXiv:2610.22367v1 Announce Type: cross Abstract: Significant efforts are currently being directed toward the implementation of large-scale quantum information processors, but realizing useful quantum
arXiv:2610.22356v1 Announce Type: new Abstract: Vision-language models still struggle to understand 3D spatial relations across views and update spatial judgments as the observer moves. A common appro
arXiv:2610.21182v1 Announce Type: new Abstract: Latent chain-of-thought replaces written reasoning steps with continuous hidden states, giving models additional steps to compute before answering. It r
arXiv:2610.20859v1 Announce Type: new Abstract: Typology-aware tokenizers are motivated by the claim that segmentation which respects morpheme boundaries preserves information that frequency-driven se
arXiv:2610.21378v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models reduce computation by routing each token to a small set of experts, but each selected expert is still used at a fixed pr
arXiv:2610.22130v1 Announce Type: new Abstract: Key-value (KV) cache management has become a critical bottleneck for scaling Large Language Models (LLMs) to long-context scenarios due to linear memory
arXiv:2610.21467v1 Announce Type: cross Abstract: Transcribing expressive piano performances into scores requires interpreting individual note timings within an underlying metrical structure. However,
arXiv:2610.21862v1 Announce Type: new Abstract: This paper introduces TagInsert, a Transformer-based model that challenges the common left-to-right (L2R) generation paradigm in Transformers, for seque
arXiv:2610.21668v1 Announce Type: new Abstract: We introduce Edit4D, an editable text-to-4D scene generation framework that constructs 4D scenes from separate background and dynamic character represen
arXiv:2610.22046v1 Announce Type: cross Abstract: Verifying the final answer of a long reasoning trace may show that the trace is wrong but it does not distinguish three cases. The problem may lie bey
arXiv:2610.21033v1 Announce Type: cross Abstract: We propose a general framework for non-interactive locally differentially private (LDP) learning of structured univariate distributions that can be ap
arXiv:2610.22290v1 Announce Type: new Abstract: Reinforcement learning has become a common post-training technique to improve the accuracy of LLMs on verifiable tasks. However, such training can narro
arXiv:2610.21368v1 Announce Type: cross Abstract: With the expansion of pre-trained language model usage in recent years, the importance of datasets for performing tasks in specialized domains has sig
arXiv:2610.22035v1 Announce Type: cross Abstract: Current heterogeneity-aware training systems for large models balance workloads by assigning unequal numbers of layers across pipeline stages, a strat
arXiv:2610.20637v1 Announce Type: new Abstract: We expand the exponential kernel of attention into a truncated Taylor series of n terms and factorize each term into a tensor-power inner product, which
arXiv:2610.20635v1 Announce Type: cross Abstract: Permutation generation with language models requires both text-conditioned ranking and a global one-to-one assignment between candidates and output po
arXiv:2606.12559v2 Announce Type: replace-cross Abstract: The ensemble Kalman filter (EnKF) is widely adopted for sequential data assimilation, but fails for solutions with discontinuities, such as sh
arXiv:2610.21547v1 Announce Type: new Abstract: Federated learning (FL) is increasingly used to adapt a pretrained, centrally fine-tuned model to data that remain on user devices, beyond training a mo
arXiv:2610.21194v1 Announce Type: cross Abstract: Existing federated data condensation methods face privacy risks, as uploaded synthetic data may preserve sensitive information and remain vulnerable t
arXiv:2610.20636v1 Announce Type: cross Abstract: Sampling from continuous flow-based generators such as flow matching models requires numerical ODE or SDE integration, making inference cost depend on
arXiv:2610.20918v1 Announce Type: cross Abstract: Utilities request mutual aid crews to restore power after severe storms, and requesting early secures more crews but relies on less accurate forecasts
arXiv:2603.11611v2 Announce Type: replace-cross Abstract: Rotary Positional Embedding (RoPE) is widely used in transformers to encode relative positional information, yet the effect of applying RoPE t
arXiv:2610.21149v1 Announce Type: new Abstract: Self-generated In-Context Learning (ICL) enables LLMs to synthesize their own few-shot demonstrations, often outperforming manual prompts. However, exis
arXiv:2610.21865v1 Announce Type: cross Abstract: Sketching is one of the most natural ways for people to express visual ideas. Unlike the text prompts that most generative systems rely on today, a sk
arXiv:2610.21667v1 Announce Type: new Abstract: As vision-language models (VLMs) transition from frozen-encoder pipelines to native multimodal architectures, the visual channel increasingly serves as
arXiv:2610.22371v1 Announce Type: new Abstract: We introduce Gen4P, a unified framework for recovering 4D geometry and motion from monocular video. We show that a pretrained video generator can be rep
arXiv:2610.22213v1 Announce Type: new Abstract: Randomized block coordinate descent (RBCD) is a popular optimization algorithm for many large-scale machine learning problems. The existing theoretical
arXiv:2610.20655v1 Announce Type: cross Abstract: We present a global-in-time spectral Duhamel-Picard method with polynomial expansions for post-exposure bake (PEB) simulation. The coupled acid-quench
arXiv:2610.22214v1 Announce Type: new Abstract: Multiple patterning lithography (MPL) has been widely used to improve lithography resolution in advanced nodes, but it faces cost limits as feature size
arXiv:2511.03068v5 Announce Type: replace Abstract: A large driver of the complexity of graph learning is the interplay between structure and features. When analyzing the expressivity of graph neural
arXiv:2610.22014v1 Announce Type: cross Abstract: Longitudinal electronic health records (EHRs) contain complementary diagnostic and laboratory information about patient health. However, irregularity,
arXiv:2610.20997v1 Announce Type: new Abstract: We study fixed-budget adaptive experimentation aimed at maximizing the probability of obtaining sufficient posterior evidence that a recommended design'
arXiv:2610.21201v1 Announce Type: new Abstract: Despite a surge of empirical interest in the ``unreasonable effectiveness'' of drastic data pruning for AI systems, a unified theoretical understanding
arXiv:2610.21329v1 Announce Type: new Abstract: Attribute-value extraction is important for building high-quality product catalogs in e-commerce. Existing systems either rely on generative or tagging
arXiv:2610.21407v1 Announce Type: new Abstract: Early stress detection and risk prediction are crucial for timely mental health assessment and support. While large language models have recently shown
arXiv:2610.21901v1 Announce Type: cross Abstract: Sequence models can generalise in fundamentally distinct ways: extrapolating structures seen in training, or using their prompt to adapt to novel task
arXiv:2610.21719v1 Announce Type: new Abstract: Arrested retinal development can cause childhood visual impairment, but grading optical coherence tomography scans is difficult to standardise across de
arXiv:2610.21179v1 Announce Type: cross Abstract: Rubrics as Rewards (RaR) extends reinforcement learning to non-verifiable domains by using an LLM judge to score responses against a structured rubric
arXiv:2610.20640v1 Announce Type: new Abstract: Global streamflow forecasting supports flood preparedness, yet data-driven models trained on reanalysis lose skill when driven by operational forecasts,
arXiv:2610.22300v1 Announce Type: cross Abstract: Not all facts a language model can recall support further learning equally well. We distinguish active facts, which support generalization beyond thei
arXiv:2610.22182v1 Announce Type: new Abstract: Few-shot adaptation often relies on an encoder's final global representation, leaving complementary information in intermediate layers underused. Combin
arXiv:2610.21176v1 Announce Type: cross Abstract: Large language models (LLMs) reproduce a human working-memory signature on the N-back task: performance declines as memory load N increases, and error
arXiv:2610.20936v1 Announce Type: new Abstract: Generating dynamically feasible motions for legged and manipulating robots requires solving a large, nonlinear, non-convex optimal control problem (OCP)
arXiv:2603.13467v2 Announce Type: replace-cross Abstract: Model merging has shown that multitask models can be created by directly combining the parameters of different models that are each specialize
arXiv:2610.21579v1 Announce Type: cross Abstract: Recent models generate sewing patterns from images or text, and program-based representations make these patterns executable. These systems produce a
arXiv:2606.12733v3 Announce Type: replace Abstract: Privacy auditing provides an important safeguard by estimating the actual information leaked by a model, thus ensuring that theoretical privacy guar
arXiv:2610.20951v1 Announce Type: new Abstract: Decision models answer typed questions about an input with one probability per option, computed in a single forward pass without generating text. Like t
arXiv:2610.22169v1 Announce Type: new Abstract: The vocabulary of a language model is its native semantics: the embedding and the unembedding fix the meaning of a state at the two ends of the residual
arXiv:2610.20825v1 Announce Type: cross Abstract: We prove the weak composition-independence conjectures of Kohn, Marchetti, Massarenti and Mella. The proof uses deformations of rational curves and a
arXiv:2610.21254v1 Announce Type: new Abstract: Cyber threat intelligence (CTI) relies on the timely identification of emerging threats, enabling organizations and security analysts to support situati
arXiv:2409.12500v2 Announce Type: replace-cross Abstract: Large language models have become increasingly popular and demonstrated remarkable performance in various natural language processing (NLP) ta
arXiv:2610.21318v1 Announce Type: cross Abstract: Multimodal document retrieval-augmented generation (RAG) has focused largely on retrieval, yet its answers depend on how well a vision-language model
arXiv:2610.09895v1 Announce Type: cross Abstract: We study a behavioral mechanism for artificial partiality in conversational agents. The paper reports no human-subjects data and makes no claim about
arXiv:2610.20870v1 Announce Type: cross Abstract: We present a generative surrogate for charged-current (nu_mu)-nucleus scattering that can be calibrated to measured differential cross sections withou