Knowledge catalogue
arXiv:2609.01091v1 Announce Type: new Abstract: Beyond intended capabilities, model distillation can transfer hidden traits from a teacher. A teacher biased by a system prompt can generate semanticall
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:2609.01158v1 Announce Type: cross Abstract: Autoencoders typically meet tight latent-memory budgets by making each latent representation smaller, sacrificing representational capacity. We ask a
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:2511.05059v3 Announce Type: replace Abstract: During laparoscopic surgery, smoke generated by tissue cauterization can significantly degrade the visual quality of endoscopic frames, increasing t
arXiv:2609.01353v1 Announce Type: new Abstract: Protein inverse folding aims to recover amino acid sequences for a given 3D protein structure, underpinning broad applications such as enzyme engineerin
arXiv:2609.00184v1 Announce Type: new Abstract: Large language models (LLMs) rely on static pretraining corpora, causing their knowledge to become outdated over time. Existing approaches for evaluatin
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:2510.17234v3 Announce Type: replace-cross Abstract: Recently, significant progress has been made in multi-modal continual learning, aiming to learn new tasks sequentially in multi-modal settings
arXiv:2609.00047v1 Announce Type: cross Abstract: Graph prompt learning is an effective paradigm to adapt pre-trained graph models to downstream tasks in low-resource scenarios. However, existing mult
arXiv:2609.00658v1 Announce Type: new Abstract: Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Ye
arXiv:2609.00802v1 Announce Type: new Abstract: Multi-party interaction is a central setting for human communication and a necessary target for human-agent interaction systems that must participate in
arXiv:2609.01515v1 Announce Type: cross Abstract: Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correla
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:2609.01076v1 Announce Type: cross Abstract: Crystal generators can now propose periodic structures, but their control interfaces remain poorly matched to the mixed descriptors used in materials
arXiv:2511.19703v2 Announce Type: replace-cross Abstract: We study the dimension and identifiability of neurovarieties associated to polynomial neural networks. We give an independent geometric proof
arXiv:2609.00264v1 Announce Type: new Abstract: Chain-of-thought monitoring is proposed for AI oversight, yet evaluations often provide monitors with a trusted reference answer. We ask whether answer
arXiv:2609.00304v1 Announce Type: new Abstract: Models express values and welfare-relevant self-reports, but it is unclear whether these outputs reflect stable preferences or a stable self. We thus in
arXiv:2609.01275v1 Announce Type: cross Abstract: Frontier AI systems function as constitutional institutions: each deployed model encodes an implicit ranking among safety, helpfulness, honesty, auton
arXiv:2609.00329v1 Announce Type: cross Abstract: Lexical normalization rewrites the noisy, non-standard words that fill user-generated text (tmrw, u, gr8) into their standard forms. Because labelled
arXiv:2609.00515v1 Announce Type: cross Abstract: Large language models (LLMs) have recently demonstrated improved machine translation performance over strong supervised baselines. This raises questio
arXiv:2609.00275v1 Announce Type: new Abstract: Fleets of LLM agents now externalize effects that cannot be fully undone: they move money, deploy code, delete data, and disclose information. Current c
arXiv:2609.01034v1 Announce Type: new Abstract: The central flow of Cohen et al. (2025) is an empirically accurate continuous-time model of gradient descent at the edge of stability in deep learning,
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:2609.01597v1 Announce Type: cross Abstract: Natural language is emerging as a primary feedback channel for improving language agents, capable of conveying intent, preferences, and causal structu
arXiv:2609.00519v1 Announce Type: cross Abstract: Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control perfo
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:2609.00868v1 Announce Type: cross Abstract: Vision-language models are evaluated by aggregate accuracy on multimodal benchmarks, a practice that implicitly assumes the model uses its visual inpu
arXiv:2609.00969v1 Announce Type: cross Abstract: We present the zbMATH Open Knowledge Graph, a large-scale RDF knowledge graph (KG) covering more than 250 years of mathematical scholarship. Unlike ex
arXiv:2602.01995v2 Announce Type: replace Abstract: Conversational diagnosis requires multi-turn history-taking, where an agent asks clarifying questions to refine differential diagnoses under incompl
arXiv:2609.01277v1 Announce Type: cross Abstract: Although pretrained joint audio-visual diffusion models offer rich control over what to generate, they provide no explicit control over when an uttera
arXiv:2609.00330v1 Announce Type: cross Abstract: In contact centers, real-time agent-assist tools determine, for each of many predefined topics, whether a live customer utterance is relevant and disp
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:2609.00597v1 Announce Type: new Abstract: With the rapid rise of large language models (LLMs), controlling undesirable model behaviors has become increasingly important. Existing behavioral cont
arXiv:2609.00463v1 Announce Type: new Abstract: This work examines recent byte-level models and their failure to perfectly manipulate characters. State-of-the-art byte-level models use a hierarchical
arXiv:2609.00296v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly proposed for healthcare tasks such as clinical documentation, evidence retrieval, patient messaging,
arXiv:2609.00455v1 Announce Type: new Abstract: Large language models (LLMs) are being used as policies for autonomous decision-making and planning in many domains. Despite their strong reasoning capa
arXiv:2609.00805v1 Announce Type: new Abstract: LLM-based software systems increasingly require effective 'evals' as quality gates in the development lifecycle. However, existing work typically addres
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:2609.01202v1 Announce Type: cross Abstract: Clinical trials are essential for advancing cancer care and drug development, but many fail because of insufficient patient enrollment. While there is
arXiv:2609.00618v1 Announce Type: cross Abstract: We investigate the role of conversational context modeling in user preference tracking for Conversational Recommendation Systems (CRSs). In this regar
arXiv:2609.00845v1 Announce Type: new Abstract: Recent advancements in Vision-Language Models (VLMs) have demonstrated impressive capabilities in static visual recognition and high-level semantic reas
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:2609.00879v1 Announce Type: new Abstract: Reliable disaster damage assessment requires models that provide both accurate predictions and transparent explanations. However, existing multimodal ap
arXiv:2609.00372v1 Announce Type: cross Abstract: With quantum sensors, simulators and networks emerging, a future of quantum technology may produce quantum states as data---that is, coherently rather
arXiv:2609.00862v1 Announce Type: new Abstract: We show that a frozen generic text-to-image diffusion model can perform conditional inpainting across three evaluated natural-image domains with one fix
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:2604.04646v2 Announce Type: replace-cross Abstract: Flow-based models learn a target distribution by modeling a marginal velocity field, defined as the average of sample-wise velocities connecti
arXiv:2609.00038v1 Announce Type: cross Abstract: Outcome-only evaluation is the production default for LLM agents: show a judge the request and the final reply and ask whether it was handled well. Th
arXiv:2609.01428v1 Announce Type: new Abstract: Large Language Model (LLM) agents based on the ReAct paradigm have demonstrated remarkable capabilities in tool use and task execution. However, ReAct s
arXiv:2609.00665v1 Announce Type: new Abstract: Edge-AI model selection is commonly driven by one isolated metric - accuracy, latency, memory, energy, or safety, even though a deployable language mode
arXiv:2609.00470v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) grounds large language models in external corpora, but implicit trust in retrieved documents creates a critical att
arXiv:2609.00300v1 Announce Type: new Abstract: Reducing the review of clearly cancer-negative screening mammograms could lower radiologist workload without compromising cancer detection. We propose a
arXiv:2609.00624v1 Announce Type: new Abstract: A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we i
arXiv:2609.00640v1 Announce Type: cross Abstract: Generalizable Audio-to-Score (A2S) transcription is fundamentally constrained by the severe scarcity of high-quality, real-world paired data. Relying
arXiv:2609.00832v1 Announce Type: new Abstract: The exponential growth of scientific publications calls for automatic Information Extraction (IE) systems to support knowledge discovery. In this contex
arXiv:2609.00335v1 Announce Type: new Abstract: A published theoretical account of phase structure in rotary attention was subjected to two pre-specified empirical tests of whether phase-derived featu
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