Knowledge catalogue
arXiv:2609.00092v1 Announce Type: new Abstract: Long-horizon complex tasks require foundation models to accumulate information, maintain internal states, and adapt over extended interactions. Safety s
arXiv:2609.00065v1 Announce Type: cross Abstract: A language-model agent asked to analyse an experiment will usually return working code. Whether the analysis is defensible is a different question. A
arXiv:2609.00654v1 Announce Type: new Abstract: We describe the SciTrue team's participation in both subtasks of the NTCIR-19 SciClaimEval task~ite{sciclaimeval}, which asks systems to verify scientif
arXiv:2609.01567v1 Announce Type: new Abstract: Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as policies is expensive and brittle: they
arXiv:2609.01426v1 Announce Type: cross Abstract: Clear cell renal cell carcinoma (CCRCC) grading is essential for treatment planning, yet existing approaches either analyze patch-level images directl
arXiv:2504.01547v3 Announce Type: replace Abstract: Supervised deep learning achieves strong performance in biomedical image segmentation but relies on costly pixel-wise annotations, motivating semi-s
arXiv:2609.00584v1 Announce Type: new Abstract: Does unrestricted AI access bypass the cognitive effort required for learning, or does it streamline knowledge acquisition? This paper reports on a stud
arXiv:2609.01279v1 Announce Type: cross Abstract: Emotion is expressed in text along a wide spectrum, from surface lexical cues to inferences entangled with content. Most layer-wise analyses of emotio
arXiv:2609.00319v1 Announce Type: cross Abstract: Online health information seeking is shifting from keyword search, where users consider a ranked list of links, to conversational systems that compose
arXiv:2603.02974v2 Announce Type: replace Abstract: DINO models provide rich patch-level representations that have recently enabled strong performance in unsupervised anomaly detection (UAD). Most exi
arXiv:2609.00427v1 Announce Type: new Abstract: The exponential growth of wireless devices is driving unprecedented spectrum demand, pushing spectrum management toward more fine-grained decisions acro
arXiv:2510.26614v2 Announce Type: replace Abstract: We propose tokenization of events and present a tokenizer, Spiking Patches, specifically designed for event cameras. Given a stream of asynchronous
arXiv:2603.16783v2 Announce Type: replace Abstract: Robust voice agents require exposure to the full diversity of how people interact through speech. However, obtaining enough spoken interactions is p
arXiv:2609.00844v1 Announce Type: new Abstract: Customer-service QA in an AI contact center (AICC) runs under deployment constraints that benchmark QA misses: tight voice-hotline latency and a high co
arXiv:2609.01146v1 Announce Type: cross Abstract: Stain normalization reduces color variations caused by variations in staining protocols and imaging conditions, thereby enhancing computer-aided diagn
arXiv:2609.00870v1 Announce Type: cross Abstract: Tensor networks, originally developed for quantum many-body physics, are promising models for machine learning. We derive stochastic Riemannian optimi
arXiv:2609.01591v1 Announce Type: new Abstract: AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for w
arXiv:2609.00789v1 Announce Type: new Abstract: The Levenberg-Marquardt (LM) algorithm is a well-known second-order method for rapid convergence and strong robustness when training small- to medium-si
arXiv:2609.01151v1 Announce Type: new Abstract: In the standard LM training pipeline, subword tokenisation is applied as a preprocessing step. Subword segmental language modelling is an alternative pa
arXiv:2508.11857v3 Announce Type: replace-cross Abstract: Tokenization remains a persistent bottleneck in language modeling, especially when vocabulary learning is limited by whitespace boundaries. We
arXiv:2603.12665v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have demonstrated significant advantages in robotic manipulation. However, their reliance on vision and language
arXiv:2609.00746v1 Announce Type: new Abstract: Fine-tuning a pretrained LLM into a vision-language model (VLM) can erode the backbone's text capability, with the damage concentrated on tasks that req
arXiv:2609.00492v1 Announce Type: new Abstract: Both privacy and factual accuracy are paramount in high-stakes domains like healthcare. Concerningly, we uncover and investigate a privacy-hallucination
arXiv:2609.01587v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is widely used to reduce the cost of serving large language models (LLMs), but its accuracy cost is uneven and is oft
arXiv:2510.11944v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) excel at both informal and formal (e.g. Lean 4) mathematical reasoning but still struggle with autoformalisation,
arXiv:2609.00050v1 Announce Type: cross Abstract: Agentic AI is enabling cloud-based workflows in which autonomous agents reason over operational state, invoke authorized tools, modify software and in
arXiv:2506.18240v5 Announce Type: replace-cross Abstract: Training quantized neural networks remains fundamentally challenging due to non-convex loss landscapes and discrete parameter spaces. We intro
arXiv:2512.03994v4 Announce Type: replace Abstract: As organizations increasingly deploy LLMs in sensitive domains such as legal, financial, and medical settings, ensuring alignment with internal orga
arXiv:2609.00028v1 Announce Type: new Abstract: Multimodal GUI agents have emerged as a promising paradigm for digital task automation, yet transitioning from benchmark-oriented models to dependable r
arXiv:2609.01598v1 Announce Type: new Abstract: Accurate segmentation of vascular structures in digital subtraction angiography (DSA) images remains challenging due to the thin, elongated, and branchi
arXiv:2609.00213v1 Announce Type: new Abstract: Reinforcement learning fine-tuning of large language models increasingly adopts multiple reward dimensions, including verifiable rules, task-specific ev
arXiv:2609.00700v1 Announce Type: new Abstract: LLMs have been rapidly adopted across writing tasks, prompting the development of tools for detecting LLM-generated text. Yet, these tools largely measu
arXiv:2609.00507v1 Announce Type: new Abstract: Accurate prediction of unsteady separated flows is challenging because the aerodynamic loads depend on nonlinear separation and vortex-shedding dynamics
arXiv:2603.29852v2 Announce Type: replace-cross Abstract: We introduce VectorGym, a comprehensive benchmark suite for Scalable Vector Graphics (SVG) that spans generation from text and sketches, compl
arXiv:2609.00898v1 Announce Type: cross Abstract: Obtaining labeled data for semantic segmentation in applied settings (e.g., autonomous driving, industrial waste sorting) is expensive and often infea
arXiv:2609.00830v1 Announce Type: cross Abstract: Whether attention weights faithfully reflect model reasoning has been actively debated in NLP, yet this question remains largely unexplored for the vi
arXiv:2609.00505v1 Announce Type: new Abstract: Video-text models adapted from image-text architectures (e.g., CLIP) frequently exhibit temporal blindness, the inability to perceive fundamental cues l
arXiv:2606.21704v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) distillation transfers multi-step reasoning from large reasoning models to smaller students, but verbose teacher traces infla
arXiv:2609.00782v1 Announce Type: new Abstract: Unsupervised feature selection seeks a compact subset of informative features without access to class labels, making feature utility difficult to define
arXiv:2609.00905v1 Announce Type: new Abstract: Sampling from distributions conditioned on desired semantic properties is an emerging challenge in modern generative modeling. Metropolis-Hastings (MH)
arXiv:2609.01103v1 Announce Type: new Abstract: Reducing the modality gap between image and text representations in CLIP is widely expected to improve cross-modal alignment and downstream performance.
arXiv:2609.00510v1 Announce Type: new Abstract: Artificial intelligence systems increasingly enact market-facing promises through chatbots, recommendation systems, automated decisions, and generative
arXiv:2609.01386v1 Announce Type: new Abstract: Tokenization in language models is treated by default as an input preprocessing decision. We argue that this framing is incomplete: in autoregressive mo
arXiv:2609.00358v1 Announce Type: new Abstract: Vision Transformers provide strong visual representations but typically rely on slowly updated parameters, limiting their ability to organize newly acqu
arXiv:2609.00568v1 Announce Type: cross Abstract: Code generation aims to automatically generate source code from task requirements and has attracted significant attention with the rapid advancement o
arXiv:2609.00188v1 Announce Type: new Abstract: Robotic manipulation faces a fundamental scaling challenge: robust generalization demands broad physical experience, yet action-labeled robot trajectori
arXiv:2608.30817v1 Announce Type: cross Abstract: Geospatial foundation models have emerged as state-of-the-art methods for downstream Earth observation tasks. However, existing pretraining methodolog
arXiv:2507.04659v3 Announce Type: replace Abstract: To address the challenges posed by the heavy reliance of multi-output models on preset probability distributions and embedded prior knowledge in non
arXiv:2608.29005v1 Announce Type: new Abstract: Camera-only end-to-end (E2E) driving models are nearing deployment, where the camera stream is degraded by blur, noise, low light, weather, frame loss,
arXiv:2301.12569v2 Announce Type: replace Abstract: Handling trust is a core requirement of effective interaction between people and AI agents. Thus, any decision-making framework designed to work wit
arXiv:2608.28846v1 Announce Type: cross Abstract: Layer-skipping methods for efficient LLM inference decide, at some granularity, which transformer layers to execute for a given input. We present a ri
arXiv:2608.29667v1 Announce Type: new Abstract: The rapid development of LLMs incurs prohibitive memory footprints and intensive computational demands. Quantization-Aware Training (QAT) techniques hav
arXiv:2608.30963v1 Announce Type: cross Abstract: Modern large language model (LLM) serving systems increasingly operate over repeated or shared context, yet each model typically performs its own pref
arXiv:2608.29831v1 Announce Type: new Abstract: Localizing issue-relevant code regions is a critical step in automated software engineering. However, due to their reliance on sparse trajectory-level s
arXiv:2608.30033v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to simulate human behavior but frequently fail to exhibit realistic cognitive constraints, sufferin
arXiv:2608.29662v1 Announce Type: new Abstract: Knowledge distillation effectively transfers reasoning capabilities from large language models to lightweight student models. To enable knowledge transf
arXiv:2608.28923v1 Announce Type: cross Abstract: Data augmentation is a cornerstone of deep learning pipelines, yet existing strategies treat it as a static, model-agnostic preprocessing step, either
arXiv:2608.29208v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models, built upon Vision-Language Models (VLMs), have significantly enhanced robotic capabilities by leveraging internet
arXiv:2608.28778v1 Announce Type: cross Abstract: Autonomous vehicles (AVs) rely on accurate camera-LiDAR calibration for multimodal sensor fusion. In practice, calibration can drift due to vibration,
arXiv:2608.29503v1 Announce Type: new Abstract: Worst-case online classification is governed by sequential complexity, such as Littlestone dimension, and can be impossible even for statistically simpl