Knowledge catalogue
arXiv:2605.29684v1 Announce Type: new Abstract: The scaling limit where both the size of the training set P and the width N of a deep neural network grow at the same rate, the so-called proportional-w
arXiv:2605.29509v1 Announce Type: new Abstract: In recent years, training-free video generation has progressed remarkably. However, when handling complex textual instructions, existing methods still s
arXiv:2605.29259v1 Announce Type: cross Abstract: Given the wide range of deployment targets, flexible model selection is essential for optimizing performance within a given compute budget. Recent wor
arXiv:2605.30245v1 Announce Type: new Abstract: Current plan-based reasoning methods improve large language models (LLMs) by inserting a planning stage before execution, giving rise to the question ri
arXiv:2605.29075v1 Announce Type: new Abstract: LLMs encode both general capabilities and domain-specific knowledge in a single set of parameters. We ask whether this capacity can be reorganized: keep
arXiv:2605.29459v1 Announce Type: new Abstract: Large language models route every input through a learned embedding table of shape |V| x d_model, consuming hundreds of millions to billions of trainabl
arXiv:2605.29009v1 Announce Type: cross Abstract: Post-training large language models with reinforcement learning is bottlenecked by the reward signal. Existing approaches require either ground-truth
arXiv:2605.29928v1 Announce Type: cross Abstract: As AI-generated and AI-assisted content floods online spaces, source labels attached to such content can distort human reasoning judgments, with downs
arXiv:2605.29888v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training has shown to improve reasoning in large language models (LLMs). However, there has been little exploration o
arXiv:2605.30115v1 Announce Type: new Abstract: This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with spars
arXiv:2605.28854v1 Announce Type: new Abstract: Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a cap
arXiv:2510.16658v3 Announce Type: replace Abstract: The development of large-scale artificial intelligence (AI) models is influencing neuroscience research by enabling end-to-end learning from raw bra
arXiv:2605.30018v1 Announce Type: new Abstract: Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabili
arXiv:2605.29384v1 Announce Type: cross Abstract: We propose Latent Terms, a method revealing that models trained for dense retrieval, whether single- or multi-vector, learn representations that can t
arXiv:2511.04934v3 Announce Type: replace Abstract: Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing
arXiv:2601.22531v2 Announce Type: replace-cross Abstract: Because of the pervasive use of deep neural networks (DNNs), especially in high-stakes domains, the interpretability of DNNs has received incr
arXiv:2605.29274v1 Announce Type: new Abstract: LLM-based automated scoring approaches near-human performance, but scaling to new tasks remains bottlenecked by the per-item human configuration of upst
arXiv:2205.04297v2 Announce Type: replace-cross Abstract: This paper proposes a learning-based visual peg-in-hole that enables training with several shapes in simulation, and adapting to arbitrary uns
arXiv:2605.29144v1 Announce Type: new Abstract: Robotics Wire Arc Additive Manufacturing (WAAM) is governed by complex and nonlinear process dynamics coupling thermal field to the build geometry. The
arXiv:2605.29610v1 Announce Type: cross Abstract: In scene graph generation, a central challenge is modeling polysemous predicates whose meanings shift across contexts. Prior approaches address this i
arXiv:2605.29421v1 Announce Type: new Abstract: Photonic crystal fiber (PCF) inverse design remains challenging because candidate geometries must satisfy coupled optical targets under expensive electr
arXiv:2605.29549v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) is a recent approach for scene rendering. Although primarily designed for view synthesis, its potential for scene understan
arXiv:2605.28990v1 Announce Type: new Abstract: Functional magnetic resonance imaging (fMRI) is a powerful tool for investigating human brain function. However, the high cost of data acquisition and t
arXiv:2605.30042v1 Announce Type: new Abstract: Automating scientific computing workflows requires more than generating executable code: autonomous systems must also select appropriate computational s
arXiv:2605.30132v1 Announce Type: new Abstract: Modern learning systems excel at interpolation but struggle to generalize to unseen tasks outside the training distribution's support. This failure occu
arXiv:2605.29572v1 Announce Type: new Abstract: Human tactile perception of materials relies on complex multisensory touch cues, yet the relationship between low-level tactile signals and perceptual r
arXiv:2605.29525v1 Announce Type: new Abstract: Deep neural networks process data through a cascade of representations: input features, hidden activations, logits, and loss. While perturbations at the
arXiv:2512.21311v2 Announce Type: replace Abstract: Solving partial differential equations (PDEs) on shapes underpins many shape analysis and engineering tasks; yet, prevailing PDE solvers operate on
arXiv:2605.30292v1 Announce Type: cross Abstract: Conformal prediction methods enjoy strong theoretical and empirical predictive inference performance, provided the data is exchangeable, and predictor
arXiv:2602.10388v3 Announce Type: replace-cross Abstract: The diversity of post-training data is critical for effective downstream performance in large language models (LLMs). Many existing approaches
arXiv:2508.19282v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual acc
arXiv:2605.29714v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are widely used to scale language models, yet their expert routing behavior and adaptation in a multilingual setting rem
arXiv:2502.07623v4 Announce Type: replace Abstract: After developing a computational system for morphological analysis of the Mapuche language, and evaluating it with texts from various authors and st
arXiv:2605.29756v1 Announce Type: new Abstract: As large language models continue to scale, low-bit weight-only post-training quantization (PTQ) offers a practical solution to their memory-efficient d
arXiv:2605.29208v1 Announce Type: cross Abstract: We describe libhmm, a C++20 library for Hidden Markov Model parameter estimation, sequence decoding, and model selection. libhmm addresses two gaps in
arXiv:2605.29092v1 Announce Type: new Abstract: Current face video forgery detectors use wide or dual-stream backbones. We show that a single, lightweight fusion of two handcrafted cues can achieve hi
arXiv:2605.28822v1 Announce Type: new Abstract: Defect grading of power transmission equipment (DGPTE) is crucial to the stability of electric energy transmission. Although existing machine learning m
arXiv:2605.29559v1 Announce Type: new Abstract: Mastering terminal environments requires language agents capable of multi-step planning, feedback-grounded execution, and dynamic state adaptation. Howe
arXiv:2605.30174v1 Announce Type: new Abstract: We introduce LiveSVG, a zero-shot approach for generating Scalable Vector Graphics (SVG) animations using video diffusion models. Current SVG animation
arXiv:2605.29649v1 Announce Type: new Abstract: Heuristic search is the dominant paradigm in symbolic AI planning, and the strongest heuristics are the result of decades of work by planning researcher
arXiv:2605.29864v1 Announce Type: new Abstract: Multi-step robot manipulation requires acting under uncertainty about how the scene will evolve, making exploration and policy adaptation challenging. W
arXiv:2605.29048v1 Announce Type: new Abstract: In this paper, we introduce LLMBridge, a new LLM based system for the task of end-to-end referential bridging resolution in English. Our bridging resolu
arXiv:2605.30348v1 Announce Type: cross Abstract: The pretraining data mixture of Large Language Models (LLMs) constitutes their 'digital DNA', shaping model behaviors, capabilities, and failure modes
arXiv:2605.30273v1 Announce Type: cross Abstract: Large language models (LLMs) show promise in generating supportive responses for mental health queries, but improving their usefulness, empathy, and s
arXiv:2605.30335v1 Announce Type: new Abstract: Multi-component LLM agents assemble probabilistic claims from components that each see only part of a joint problem; the composition can violate basic p
arXiv:2510.26412v3 Announce Type: replace-cross Abstract: Recent advances in text-to-video generation have achieved impressive performance on short clips, yet evaluating long-form generation under com
arXiv:2605.28876v1 Announce Type: cross Abstract: CI failure logs are large (median 5k lines, max 200k in this corpus) and noisy. Coding agents that try to debug them depend on an upstream tool to red
arXiv:2605.30265v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image
arXiv:2510.24606v2 Announce Type: replace Abstract: The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is of
arXiv:2502.10205v3 Announce Type: replace Abstract: Representation learning produces models in different domains, such as store purchases, client transactions, and general people's behavior. However,
arXiv:2411.14279v2 Announce Type: replace-cross Abstract: Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising per
arXiv:2605.30274v1 Announce Type: cross Abstract: Document-level translation remains one of the most challenging tasks for large language models, which are constrained by limited context windows that
arXiv:2605.29280v1 Announce Type: cross Abstract: Knowledge distillation (KD) transfers a single scalar prediction from a large foundation model (FM) to compact vertical models (VMs), suffering from d
arXiv:2605.29005v1 Announce Type: cross Abstract: Diffusion-based neural solvers for combinatorial optimization repeatedly re-evaluate dense edge/factor interactions, making inference expensive in wal
arXiv:2605.29798v1 Announce Type: new Abstract: Reliable identification of fracture origins in alumina matrix composite hip and knee implants is critical for quality assurance and patient safety, yet
arXiv:2601.06431v3 Announce Type: replace Abstract: Instruction following is critical for large language models, yet real-world instructions often involve multiple constraints with logical structures,
arXiv:2603.14644v3 Announce Type: replace-cross Abstract: Publicly available full-field digital mammography (FFDM) datasets remain limited in size, clinical annotations, and vendor diversity, hinderin
arXiv:2601.04633v2 Announce Type: replace Abstract: Machine-Generated Text (MGT) is becoming increasingly difficult to distinguish from Human-Written Text (HWT). This trend has exacerbated malicious a
arXiv:2605.29940v1 Announce Type: new Abstract: Large language models (LLMs) have been widely adopted for synthetic data generation, significantly reducing annotation costs. However, most existing stu
arXiv:2605.28980v1 Announce Type: cross Abstract: Given a matrix X, and two ranks r_1 and r_2, the Hadamard decomposition (HD) looks for two low-rank matrices, X_1 of rank r_1 and X_2 of rank r_2, bot