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:2609.00618v1 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: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:2609.00685v1 Announce Type: cross Abstract: Article-level news stance detection aims to identify the perspective of news articles toward social issues. Despite advances in stance detection and i
arXiv:2609.00443v1 Announce Type: cross Abstract: Language models learn about grammatical number primarily from co-occurrence, and show frequency effects as a result---sometimes taken to indicate that
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:2608.28592v1 Announce Type: new Abstract: Large language models (LLMs) achieve high scores on medical knowledge examinations, yet real-world oncology is not a knowledge test--it is a sequence of
arXiv:2608.30656v1 Announce Type: new Abstract: Proactive tamper localization embeds an imperceptible signal into an image prior to distribution, enabling pixel-level manipulation detection. Existing
arXiv:2606.18613v4 Announce Type: replace-cross Abstract: The most plausible near-term role of medical LLMs is to assist rather than replace physicians, yet current evaluations often test isolated cap
arXiv:2608.29529v1 Announce Type: cross Abstract: Semantic alignment between specialized normative texts is challenging when equivalent requirements use different terms, syntax, and levels of abstract
arXiv:2608.30092v1 Announce Type: cross Abstract: We present Arkios, a 1.04B-parameter dense transformer pretrained from scratch on 150B tokens of bilingual English-Nepali text, using a custom single-
arXiv:2608.30373v1 Announce Type: new Abstract: Multi-Agent Debate (MAD) has been widely adopted to improve LLM-based evaluation by prompting multiple agents to negotiate and reach a consensus. Howeve
arXiv:2608.30333v1 Announce Type: cross Abstract: Next-basket repurchase recommendation is commonly formulated as a ranking task: given a customer's purchase history, the system ranks previously purch
arXiv:2608.28649v1 Announce Type: cross Abstract: Touchpoint selection in conversion attribution, namely identifying meaningful touchpoints contributing to conversions, is essential for e-commerce rec
arXiv:2608.30922v1 Announce Type: new Abstract: Masked diffusion language models predict tokens from a partially observed response canvas, enabling bidirectional conditioning and parallel token refine
arXiv:2608.28599v1 Announce Type: new Abstract: Clinical diagnosis is a step-by-step, cost-aware process: a physician orders examinations one at a time, observes the results, and updates the diagnosis
arXiv:2608.30758v1 Announce Type: new Abstract: Recent radiology multi-modal language models have made substantial progress in chest X-ray report generation, visual question answering, and temporal re
arXiv:2608.30397v1 Announce Type: new Abstract: Natural-language critiques provide supervision beyond scalar rewards for non-verifiable generation, which lacks deterministic verifiers. In critique-gui
arXiv:2608.30183v1 Announce Type: cross Abstract: Lightweight channel attention mechanisms are widely used in image classification, yet their effectiveness in fine-grained visual recognition (FGVR) re
arXiv:2602.05863v3 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) remains the dominant critic-free approach for fine-tuning LLMs and VLMs, but its compatibility with
arXiv:2608.30315v1 Announce Type: cross Abstract: Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern lan
arXiv:2601.12208v2 Announce Type: replace Abstract: Evaluating conversational systems in multi-turn settings remains a fundamental challenge. Conventional pipelines typically rely on manually defined
arXiv:2608.29307v1 Announce Type: cross Abstract: Language models increasingly answer questions by consulting retrieved documents rather than memory alone, a design now common in search assistants and
arXiv:2607.02290v2 Announce Type: replace Abstract: Recent image generation and editing models can produce visually appealing natural images, yet they remain unreliable when the target image is a know
arXiv:2608.30327v1 Announce Type: new Abstract: Fine-tuning can improve legal question-answering accuracy without improving how models use law supplied in context. We study this distinction in bilingu
arXiv:2608.29037v1 Announce Type: cross Abstract: Real-world degradations such as blur, shadow, distortion, and moire patterns severely impair the document question-answering capabilities of Multimoda
arXiv:2603.16622v2 Announce Type: replace Abstract: Instead of directly distilling a language model, this study addresses the problem of aligning a base model with a target model in distribution by de
arXiv:2608.30893v1 Announce Type: new Abstract: Electrocardiogram (ECG) interpretation requires knowledge of cardiology, electrophysiology, clinical diagnosis, ECG waveforms, signal acquisition, and i
arXiv:2608.29543v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have established conversational text-to-SQL as a practical interface between users and databases, ofte
arXiv:2606.13120v2 Announce Type: replace Abstract: Search Agents -- large language models augmented with search tools -- have intensified the need for future-proof evaluation benchmarks. Existing ben
arXiv:2608.29387v1 Announce Type: new Abstract: Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests e
arXiv:2506.11635v2 Announce Type: replace-cross Abstract: Credit card fraud mitigation plays a significant role in modern society. While fraud detection systems are essential, they often struggle to k
arXiv:2608.31033v1 Announce Type: new Abstract: Lightstage facial capture produces production-quality digital humans, but it is resource and labor-intensive. Multi-camera setups, hours of computation,
arXiv:2608.29336v1 Announce Type: new Abstract: FISICA is a body-assessment and recommendation service running in production. One standing session with two photographs returns foot-loading measures, p
arXiv:2606.12683v2 Announce Type: replace Abstract: Over the last decade, building human-level artificial general intelligence has moved from far-fetched speculation to being a concrete next-decade ta
arXiv:2608.28642v1 Announce Type: new Abstract: Knowledge graphs used by agentic systems are often treated as flat stores of extracted triples, with little record of who owns a fact, why it was admitt
arXiv:2608.30461v1 Announce Type: new Abstract: Trajectory data is getting more vital for training large language models for boosting the agentic abilities. Unlike the verifiable domains such as codin
arXiv:2503.04822v2 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) have demonstrated success in modeling relational data primarily under the assumption of homophily. However, many
arXiv:2601.08626v4 Announce Type: replace Abstract: Large language models (LLMs) excel at semantic understanding, yet their ability to reconstruct internal structure from scrambled inputs remains unde
arXiv:2602.06181v2 Announce Type: replace Abstract: Post-training quantization reduces the memory needed to run large language models but alters their social biases in ways that aggregate metrics fail
arXiv:2603.22978v2 Announce Type: replace Abstract: In the maintenance of complex systems, fault trees are used to locate problems and provide targeted solutions. To enable fault trees stored as image
arXiv:2608.29257v1 Announce Type: new Abstract: Multiple-choice questions (MCQs) are a standard format for evaluating large language models (LLMs), yet the popularity of answer options can confound ev
arXiv:2608.28860v1 Announce Type: new Abstract: Large Language Models (LLMs) often answer the same factual question differently across languages. We study whether cross-lingual latent-space interventi
arXiv:2608.29305v1 Announce Type: cross Abstract: Large language model (LLM) agents have demonstrated remarkable proficiency in manually constructed environments, yet their performance frequently coll
arXiv:2608.28926v1 Announce Type: new Abstract: We propose a multi-task learning approach for multi-party dialogue intent recognition that leverages an auxiliary task that models turn-taking dynamics.
arXiv:2608.30235v1 Announce Type: new Abstract: Knowledge graph completion requires models to use both textual descriptions and relational structure. Existing LLM-based methods either encode KG struct
arXiv:2608.31016v1 Announce Type: cross Abstract: Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the no
arXiv:2510.09347v2 Announce Type: replace Abstract: Unlike Business-to-Consumer e-commerce platforms (e.g., Amazon), inexperienced individual sellers on Consumer-to-Consumer platforms (e.g., eBay) oft
arXiv:2608.30563v1 Announce Type: new Abstract: Multimodal Emotion Recognition (MER) systems often suffer from missing modalities in real-world scenarios. Existing methods usually generate, align, or
arXiv:2608.30662v1 Announce Type: new Abstract: This paper presents Murano, an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language mode
arXiv:2608.29589v1 Announce Type: new Abstract: Text-to-image (T2I) safety guardrails fail to generalize equitably to non-standard dialects. Evaluating 23,080 paired prompts across five English dialec
arXiv:2608.30247v1 Announce Type: new Abstract: Recent unified open-vocabulary detection (OVD) supports heterogeneous prompts, including text queries, visual exemplars, and their combinations, but oft
arXiv:2603.19843v2 Announce Type: replace-cross Abstract: The ubiquity of multimedia content is reshaping online information spaces, particularly in social media environments. At the same time, search
arXiv:2608.30241v1 Announce Type: new Abstract: Recent efforts have aimed to automate scientific diagram generation from paper content (Lin et al., 2026; Zhu et al., 2026a). However, fully satisfying
arXiv:2608.30553v1 Announce Type: cross Abstract: Generative Retrieval (GR) has emerged as a promising paradigm by mapping queries directly to Semantic IDs (SIDs) with powerful representation capabili
arXiv:2608.25992v2 Announce Type: replace Abstract: Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative rea
arXiv:2508.02208v3 Announce Type: replace-cross Abstract: Evaluating the mathematical capability of Large Language Models (LLMs) is a critical yet challenging frontier. Existing benchmarks fall short,
arXiv:2608.28433v2 Announce Type: replace Abstract: Proof assistants such as Lean 4 promise the paradigm of formally verified mathematics, but large-scale formalization projects have faced major barri
arXiv:2608.28622v1 Announce Type: cross Abstract: Large language model training corpora grow through successive, often redundant releases, so each release must be deduplicated against both itself and