Diffusion transformer (DiT) research on image generation has converged to a single evaluation setup: class-conditional generation on ImageNet. While methods improve the FID and related metrics,…
Long-context reasoning is an essential capability for large language models, particularly when they are deployed as autonomous agents that must reason over lengthy trajectories. Reinforcement learning…
arXiv:2606.24064v1 Announce Type: new Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather…
arXiv:2606.23915v1 Announce Type: new Abstract: Practice often treats automatic metrics for attribution in LLM retrieval-augmented generation as interchangeable. We audit eight automatic scorers -- lexical, embedding,…
arXiv:2606.23989v1 Announce Type: new Abstract: End-to-end large language models (LLMs) produce fluent multi-document summaries but remain prone to hallucination, and the attributions they offer are typically…
arXiv:2606.23741v1 Announce Type: new Abstract: Causal reasoning, which encompasses the discovery of causal structures and the inference of causal effects, is fundamental to data-driven decision making.…
arXiv:2511.21945v3 Announce Type: replace Abstract: Generating complete 3D objects under partial occlusions (i.e., amodal scenarios) is a practically important yet challenging problem, as large portions of…
arXiv:2606.24051v1 Announce Type: new Abstract: Vision-Language-Action driving models convert a pretrained Vision-Language Model into a driving policy, allowing them to use world knowledge and follow language…
arXiv:2606.24348v1 Announce Type: cross Abstract: The growing reliance on machine learning for decisions across sectors underscores the importance of model transparency and interpretability. Existing post hoc…
arXiv:2601.21860v3 Announce Type: replace-cross Abstract: The reconstruction and inference of stochastic dynamical systems from data is a fundamental task in inverse problems and statistical learning. While…
arXiv:2605.27729v3 Announce Type: replace-cross Abstract: The 2024-2025 Nobel and Turing awards recognised AI and quantum science simultaneously. Yet no deployed system has brought these streams together…
arXiv:2606.21366v2 Announce Type: replace-cross Abstract: This work examines sexualised AI-generated English-speaking voices offered by a popular commercial platform. New technologies may enable sexual empowerment and greater…
arXiv:2505.18542v4 Announce Type: replace Abstract: Extracting structured procedural knowledge from unstructured business documents is a critical yet unresolved bottleneck in process automation. While prior work has…
arXiv:2509.24118v2 Announce Type: replace Abstract: Electronic health Records (EHRs) have become a cornerstone in modern-day healthcare. They are a crucial part for analyzing the progression of…
arXiv:2605.12218v2 Announce Type: replace Abstract: Bird's-eye-view (BEV) representations derived from multi-camera input have become a central interface for online high-definition (HD) map construction. However, most approaches…
arXiv:2508.16650v3 Announce Type: replace-cross Abstract: Brain tumour MRI typically requires both pre- and post-contrast imaging, but gadolinium is not always desirable (frequent follow-up, renal impairment, allergy,…
arXiv:2606.18074v2 Announce Type: replace Abstract: Causal discovery seeks to uncover the causal dependencies among variables. For this purpose, we propose an algorithm called Tensor-based Second-order Causal…
arXiv:2507.11768v3 Announce Type: replace Abstract: Bayesian accounts of in-context learning face a direct objection: exact posterior predictives for exchangeable data are invariant to task-preserving order, yet…
arXiv:2412.08147v2 Announce Type: replace-cross Abstract: Pareto fronts are useful to find good task-mixing strategies for multitask finetuning, but they are also costly to compute. To reduce…
arXiv:2606.24099v1 Announce Type: new Abstract: Algorithms have become central to scientific research in the era of artificial intelligence (AI). Although algorithm mentions in papers are often…
arXiv:2606.23881v1 Announce Type: new Abstract: Knowledge-Based Visual Question Answering (KB-VQA) requires grounding visual queries to external knowledge beyond directly observable content in images. While recent multi…
arXiv:2606.23992v1 Announce Type: new Abstract: Clinical value sets define the standardized terminology codes used in quality measurement, phenotyping, cohort construction, and clinical decision support. The recently…
arXiv:2606.23838v1 Announce Type: new Abstract: When two or more parameters or labels produce similar data, they are degenerate, or hard to distinguish. Degeneracies render both label…
arXiv:2606.23892v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used as perception-reasoning backbones for embodied intelligence in safety-critical physical systems, where perception or reasoning errors…