Knowledge catalogue
arXiv:2609.32288v1 Announce Type: new Abstract: Pre-training data poisoning of large language models is usually studied using targeted backdoors and their survival through safety post-training, which
arXiv:2609.33708v1 Announce Type: new Abstract: How does compositional reasoning emerge during learning? We address this question by mathematically analyzing the learning dynamics of deep linear netwo
arXiv:2609.33727v1 Announce Type: cross Abstract: Knowledge Distillation (KD) has emerged as a vital paradigm for transferring the capabilities of high-capacity models to efficient ``student'' counter
arXiv:2609.31821v1 Announce Type: new Abstract: Developing label-efficient models is a central challenge in surgical AI due to the high cost and scarcity of expert annotation. While self-supervised fo
arXiv:2510.24795v3 Announce Type: replace Abstract: Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-wor
arXiv:2408.14518v3 Announce Type: replace-cross Abstract: Simultaneous localization and mapping (SLAM) allows a mobile robot or autonomous vehicle to build a map of an unknown environment while estima
arXiv:2609.32149v1 Announce Type: cross Abstract: Linear bandits model sequential decision-making problems with noisy rewards that are linear in the decision variable, where an agent must simultaneous
arXiv:2609.35703v1 Announce Type: new Abstract: Reliable deployment of graph neural networks requires calibration, out-of-distribution (OOD) detection, and robustness to distribution shift, yet existi
arXiv:2609.34750v1 Announce Type: cross Abstract: Concept-based explanations describe neural network predictions through human-understandable properties of inputs called concepts. The field encompasse
arXiv:2609.33449v1 Announce Type: new Abstract: Historical manuscript illustrations preserve rich visual evidence of past cultures. They depict people, animals, plants, diagrams, music notations, and
arXiv:2609.34173v1 Announce Type: cross Abstract: Symmetry (or invariance) is a powerful structural property that enables efficient, effective solutions for estimation and control. However, the constr
arXiv:2609.34374v1 Announce Type: new Abstract: Language model post-training is often bottlenecked by the need for human-collected preference data, which is expensive and difficult to scale. Reinforce
arXiv:2601.00416v2 Announce Type: replace Abstract: Functional connectivity (FC) analysis, a valuable tool for computer-aided brain disorder diagnosis, traditionally relies on atlas-based parcellation
arXiv:2609.33176v1 Announce Type: new Abstract: In recent years, bilevel optimization has been widely used in a variety of machine learning tasks. However, prior bilevel optimization algorithms genera
arXiv:2609.34818v1 Announce Type: cross Abstract: AlphaFold2 is written in JAX, so the same inference code compiles and runs unchanged on CPUs, GPUs and Google Cloud TPUs. That portability makes the a
arXiv:2609.29902v1 Announce Type: cross Abstract: A new proposal called DM-SMC (Diffusion Model - Sequential Monte Carlo) is investigated, which samples ensembles defined in terms of an action, using
arXiv:2609.33832v1 Announce Type: cross Abstract: World-action models can jointly predict future visual observations and robot actions. However, discrepancies may exist between their visual prediction
arXiv:2609.31759v1 Announce Type: cross Abstract: Domain Generalization (DG) aims to develop models that remain robust to conditions unseen during training. While DG has been systematically studied in
arXiv:2609.34558v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) face significant computational inefficiencies caused by the large number of visual tokens. Existing visual token pr
arXiv:2510.26672v2 Announce Type: replace-cross Abstract: At the heart of reinforcement learning are actions -- decisions made in response to observations of the environment. Actions are equally funda
arXiv:2609.34730v1 Announce Type: new Abstract: We present an action sequence transfer system that adaptively transfers user action sequences across different target spaces. Given an input action sequ
arXiv:2609.32752v1 Announce Type: cross Abstract: Reward shaping has a theorem: a potential-based term can be removed without changing the optimal policy. The same practice on the action channel, an o
arXiv:2602.20502v2 Announce Type: replace-cross Abstract: Many web agents operate through a reactive execution loop: they observe the current interface, reason about the next action, execute it, and r
arXiv:2609.33256v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models map visual observations and language instructions directly to robot actions, but they do not explicitly represent th
arXiv:2609.34547v1 Announce Type: new Abstract: Video-capable vision-language models score above 80% on popular benchmarks yet struggle with spatial-temporal binding: associating the right action with
arXiv:2609.34982v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown great promise for robotic manipulation by mapping multi-modal semantics to physical actions. However, thi
arXiv:2609.32530v1 Announce Type: new Abstract: Difference-in-means steering requires activations recorded while a model shows the desired behavior, which a sandbagging model withholds by deliberately
arXiv:2609.32099v1 Announce Type: new Abstract: The craft of weaving, where different materials are interlaced, has tremendous potential for creating active and functional systems for use in soft robo
arXiv:2609.31675v1 Announce Type: new Abstract: We introduce the Active Causal Discovery Benchmark (ACDB), an SCM-grounded environment for evaluating whether LLM agents recover causal graph structure
arXiv:2609.32252v1 Announce Type: cross Abstract: Acquiring data is costly: higher measurement fidelity costs power and storage and risks collecting irrelevant content, while aggressive cost reduction
arXiv:2609.32325v1 Announce Type: new Abstract: In many prediction tasks, acquiring all features can be a prohibitively expensive or outright impossible task. Further, in many cases a static subset of
arXiv:2609.34085v1 Announce Type: cross Abstract: Autonomous driving requires extit{world models} that can understand the physical world, reason and plan, and operate safely. In this paper, we first s
arXiv:2510.27047v2 Announce Type: replace Abstract: This paper presents the Autonomous Driving Segment Anything Model (AD-SAM), a foundation-model adaptation framework for semantic segmentation in aut
arXiv:2510.13680v2 Announce Type: replace Abstract: Preconditioned methods are central to deep learning optimization. Predominant approaches include computationally light diagonal preconditioners such
arXiv:2609.33978v1 Announce Type: cross Abstract: Neural operators can accelerate repeated nonlinear mechanics calculations, but their accuracy can deteriorate as operating conditions move beyond the
arXiv:2609.32464v1 Announce Type: new Abstract: Multi-objective Bayesian optimization (MOBO) commonly relies on independent Gaussian processes (GPs) with stationary kernels, limiting its ability to re
arXiv:2609.31690v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) solutions are essential for building trust in AI technologies and their integration in real manufacturing line
arXiv:2609.32976v1 Announce Type: new Abstract: Incorrect or corrupted labels in tabular datasets can significantly degrade supervised learning performance, particularly when mislabeling is subtle and
arXiv:2609.32921v1 Announce Type: new Abstract: We introduce Adaptive LeWorldModel (ALeWM), a world model based on a joint-embedding predictive architecture (JEPA) that learns to concentrate predictiv
arXiv:2609.35415v1 Announce Type: cross Abstract: Frozen adaptive cruise control (ACC) policies can violate constraints when deployment dynamics differ from their training conditions. We propose resid
arXiv:2603.12057v3 Announce Type: replace Abstract: Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various rea
arXiv:2609.35021v1 Announce Type: new Abstract: Spatiotemporal prediction aims to learn discriminative representations from correlated temporal signals over spatial structures for accurate future infe
arXiv:2602.14907v3 Announce Type: replace-cross Abstract: Adjoint-based shape optimization of ship hulls is a powerful tool for addressing high-dimensional design problems in naval architecture, parti
arXiv:2609.34944v1 Announce Type: cross Abstract: Flow-based Vision-Language-Action (VLA) policies are typically trained by behavior cloning and thus do not explicitly optimize long-term task return.
arXiv:2609.34433v1 Announce Type: new Abstract: Generating a plausible clinical trajectory does not establish what would happen under a different treatment. We present ADMIT, a framework combining irr
arXiv:2609.34034v1 Announce Type: cross Abstract: A central aim of neuromorphic computing is to provide a viable alternative to highly energy-intensive Transformer-based AI. However, efficient alterna
arXiv:2005.08844v3 Announce Type: replace Abstract: We apply entropy to reinforcement learning in two ways: entropy-augmented reward defines the soft objective, while relative-entropy regularization c
arXiv:2609.35090v1 Announce Type: new Abstract: Video-text pretraining has achieved remarkable progress through the scaling of models and datasets, yet the quality of language supervision remains unde
arXiv:2609.34094v1 Announce Type: new Abstract: Identifying individual animals is crucial for effective wildlife monitoring and conservation efforts. Recent advancements in computer vision have shown
arXiv:2609.35212v1 Announce Type: new Abstract: Multi-view clustering aims to capture cross-view consistency while exploiting view-specific information. However, shared representations learned to capt
arXiv:2602.01750v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned
arXiv:2609.32411v1 Announce Type: cross Abstract: Bayesian state estimation for high-dimensional nonlinear dynamical systems entails a fundamental tension between statistical fidelity and computationa
arXiv:2609.34594v1 Announce Type: new Abstract: Accurate capture of non-cooperative targets is critical. In an attempt to tackle this intractable challenge, an aerial gripper system integrated with a
arXiv:2605.05586v2 Announce Type: replace Abstract: High-fidelity CFD is essential for aerodynamic design, but repeated simulations are computationally expensive, motivating surrogate models for rapid
arXiv:2609.33230v1 Announce Type: new Abstract: FMCW LiDAR measures per-point radial Doppler velocity alongside range, providing a motion cue unavailable in conventional time-of-flight sensors. Exploi
arXiv:2609.32695v1 Announce Type: cross Abstract: We study how the affine geometry of finite ReLU networks is created at random initialization and reorganized by supervised training. We call a sign-ch
arXiv:2609.32292v1 Announce Type: new Abstract: Vision-and-language navigation increasingly relies on general-purpose semantic planners, yet translating correct high-level intent into reliable physica
arXiv:2609.33192v1 Announce Type: new Abstract: Scientific code generation can produce executable programs that fail to compute the intended scientific object. We study this problem in language-model
arXiv:2609.31666v1 Announce Type: cross Abstract: Digital pens are widely used to capture handwriting on digital devices, enabling precise trace recording and enhancing human-computer interaction. How
arXiv:2609.32593v1 Announce Type: new Abstract: Current machine learning algorithms primarily rely on instantaneous signals such as loss, margin, and prediction confidence to characterize model behavi