Knowledge catalogue
arXiv:2605.24055v1 Announce Type: cross Abstract: Real-world time-series data in industrial sensing, healthcare, and energy systems is often corrupted by a mixture of Gaussian noise and occasional lar
arXiv:2605.24609v1 Announce Type: cross Abstract: Artificial intelligence is increasingly integrated into radiotherapy workflows, yet such pipelines remain vulnerable to out-of-distribution image data
arXiv:2605.23925v1 Announce Type: cross Abstract: Intelligent tutoring systems increasingly provide automated feedback on student work, but robust feedback requires assessing reasoning, not only final
arXiv:2605.25998v1 Announce Type: new Abstract: Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and
arXiv:2605.25891v1 Announce Type: cross Abstract: We find a mismatch between what large language models encode about a causal question and what they answer. On anti-commonsense CLadder items, a fixed
arXiv:2605.26029v1 Announce Type: new Abstract: We introduce CausaLab, a scalable environment for evaluating interactive causal discovery by LLM agents. Unlike prior evaluations, CausaLab evaluates bo
arXiv:2605.25338v1 Announce Type: cross Abstract: Large language model (LLM) agents frequently fail on multi-step tasks involving reasoning, tool use, and environment interaction. While such failures
arXiv:2605.25352v1 Announce Type: cross Abstract: Deep learning models are vulnerable to adversarial perturbations, raising important concerns for safety-critical deployment. Empirical defenses can ac
arXiv:2510.26418v4 Announce Type: replace Abstract: Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reas
arXiv:2605.24418v1 Announce Type: new Abstract: Federated learning is used in medical imaging where privacy prohibits centralizing data. Standard federated algorithms assume homogeneous hardware, iden
arXiv:2605.24340v1 Announce Type: new Abstract: Production deep learning systems across enterprise domains operate under constraints that academic benchmarks routinely obscure: labeled data is expensi
arXiv:2605.26089v1 Announce Type: cross Abstract: We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlik
arXiv:2605.24305v1 Announce Type: cross Abstract: Standard accuracy on binary reasoning benchmarks hides critical failure modes: prior collapse, inconsistency under paraphrase, and inability to reason
arXiv:2603.18908v4 Announce Type: replace Abstract: Language models increasingly appear to learn similar representations, despite differences in training objectives, architectures, and data modalities
arXiv:2605.24210v1 Announce Type: new Abstract: What functions can Neural Processes represent? We analyze the representational capacity of popular NP architectures: Conditional Neural Processes (CNPs)
arXiv:2410.19248v2 Announce Type: replace Abstract: Quality of Service (QoS) is an important metric to measure the performance of network services. Nowadays, it is widely used in mobile edge environme
arXiv:2605.25290v1 Announce Type: cross Abstract: Online experiments in ads, recommendation, and member-experience systems are often planned before the dominant interference mechanism is known. A trea
arXiv:2510.02361v2 Announce Type: replace-cross Abstract: Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to t
arXiv:2605.26036v1 Announce Type: new Abstract: Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundat
arXiv:2605.25204v1 Announce Type: new Abstract: Pluralistic alignment requires systems to adapt to diverse user values, communication styles, and contextual assumptions. We believe that a foundational
arXiv:2605.25831v1 Announce Type: cross Abstract: Large language models (LLMs) define a distribution over text, which can be viewed as a probabilistic representation of uncertainty: sampling K respons
arXiv:2605.26086v1 Announce Type: new Abstract: Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Y
arXiv:2506.17629v2 Announce Type: replace-cross Abstract: Embodied Visual Reasoning (EVR) seeks to follow complex, free-form instructions based on egocentric video, enabling semantic understanding and
arXiv:2605.25662v1 Announce Type: new Abstract: Graph neural networks for node classification are typically trained by gradient descent over hundreds or thousands of epochs. Recent work has shown that
arXiv:2605.24872v1 Announce Type: new Abstract: Conformal prediction provides distribution-free coverage guarantees, but in many-class classification it may still under-cover specific classes or subpo
arXiv:2510.19328v2 Announce Type: replace Abstract: Ensuring that predicted probabilities align with observed frequencies is critical in high-stakes domains such as clinical decision support, autonomo
arXiv:2605.24867v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) on text-attributed graphs (TA
arXiv:2605.24422v1 Announce Type: cross Abstract: Stochastic Dominance (SD) theory provides a rigorous framework for selecting superior assets tailored to the asset allocation needs of investors with
arXiv:2605.25708v1 Announce Type: cross Abstract: Multi-domain task-incremental learning requires a model to sequentially acquire knowledge across visually diverse domains without forgetting prior tas
arXiv:2605.24460v1 Announce Type: cross Abstract: Automatically mapping and segmenting global mining footprints using remote sensing and deep learning is critical for monitoring the socio-environmenta
arXiv:2605.24453v1 Announce Type: cross Abstract: Large Language Model (LLM)-based code analysis tools are adopted to automate software documentation tasks. However, the scalability of these approache
arXiv:2605.25430v1 Announce Type: new Abstract: Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled in
arXiv:2508.03526v2 Announce Type: replace Abstract: One central goal of robotics is to enable robots to interact with the physical world. Traditional manipulation studies primarily focus on single rob
arXiv:2605.25378v1 Announce Type: cross Abstract: Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Ada
arXiv:2604.18179v2 Announce Type: replace-cross Abstract: Hosted-LLM providers have a silent-substitution incentive: advertise a stronger model while serving cheaper replies. Probe-after-return scheme
arXiv:2505.11788v2 Announce Type: replace-cross Abstract: To support emerging language-based applications using dispersed and heterogeneous computing resources, the hybrid language model (HLM) offers
arXiv:2605.24779v1 Announce Type: cross Abstract: Submodular optimization has become a fundamental paradigm for data selection, retrieval, summarization, and representation learning due to its ability
arXiv:2605.25672v1 Announce Type: new Abstract: In this paper, we address the challenge of performing non-prehensile pushing operations with a compliant robotic manipulation system. To ensure safe ope
arXiv:2605.25553v1 Announce Type: cross Abstract: Category-level object pose estimation aims to predict the pose and size of arbitrary objects in specific categories. Existing methods struggle with th
arXiv:2310.04981v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) transform environment percepts into vision-language semantics interpretable by LLMs. However, completing complex
arXiv:2605.24294v1 Announce Type: cross Abstract: Android malware detectors often degrade after deployment because of concept drift, while full retraining at each maintenance step is costly. We propos
arXiv:2605.25765v1 Announce Type: cross Abstract: Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attracti
arXiv:2605.24399v1 Announce Type: new Abstract: Healthcare models are transitioning from unimodal prediction toward multimodal reasoning over heterogeneous diagnostic inputs. In computational patholog
arXiv:2605.26067v1 Announce Type: cross Abstract: Conditionally positive definite (CPD) kernels are defined with respect to a function class F. It is well known that such a kernel K is associated with
arXiv:2605.24786v1 Announce Type: cross Abstract: Long-horizon LLM inference turns the key--value (KV) cache into the dominant GPU memory consumer and makes per-token attention increasingly expensive.
arXiv:2605.26045v1 Announce Type: cross Abstract: Activation oracles aim to make the activations of other models legible to humans and yield promising results compared to white-box interpretability te
arXiv:2605.23909v1 Announce Type: new Abstract: We investigate the calibration of large language models' (LLMs') confidence across diverse tasks. The results of our preregistered study show that the c
arXiv:2605.25882v1 Announce Type: new Abstract: Recent advances in uncertainty quantification increasingly emphasise the distinction between aleatory and epistemic uncertainty in machine learning, mot
arXiv:2605.25235v1 Announce Type: cross Abstract: We give an attribution method for neural combinatorial-optimisation (CO) policies that (i) decomposes a decision by constraint families via LP-relaxat
arXiv:2605.25354v1 Announce Type: new Abstract: While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamical
arXiv:2605.25835v1 Announce Type: cross Abstract: This paper examines the specialization of Small Language Models (SLMs) with up to 4 billion parameters for generating artifacts in domain-specific lan
arXiv:2605.23928v1 Announce Type: new Abstract: We present Context, the intelligence layer of the Magarshak Architecture, which replaces reactive query-response chatbots with proactive goal-directed a
arXiv:2605.24279v1 Announce Type: new Abstract: A frontier language model's acknowledged 'helpful programming assistant' persona does not survive long agentic-coding sessions in the deployment regime
arXiv:2602.08499v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language mode
arXiv:2605.25962v1 Announce Type: cross Abstract: Machine unlearning removes designated concepts or knowledge from pre-trained models. Recent work has extended this paradigm to speaker identity unlear
arXiv:2605.25225v1 Announce Type: cross Abstract: Mechanistic interpretability often uses activation patching, causal tracing, path patching, and steering directions to reveal behaviorally meaningful
arXiv:2605.22634v2 Announce Type: replace-cross Abstract: Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings
arXiv:2605.25006v1 Announce Type: cross Abstract: Sampling-based algorithms for robot path planning offer probabilistic completeness and strong empirical convergence properties across environments wit
arXiv:2506.17326v3 Announce Type: replace Abstract: Class imbalance remains a practical obstacle in the development of clinical prediction models for conditions such as diabetes mellitus, where the nu
arXiv:2605.24812v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planni