Knowledge catalogue
arXiv:2511.22396v2 Announce Type: replace-cross Abstract: Recent multimodal reasoning models, inspired by DeepSeek-R1, have significantly advanced vision-language systems. However, in remote sensing (
arXiv:2604.07120v1 Announce Type: cross Abstract: Current operational Earth Observation (EO) services, including the Copernicus Emergency Management Service (CEMS), the European Forest Fire Informatio
The ASUS UGen300 is a plug-and-play USB AI accelerator featuring a Hailo-10H processor that delivers up to 40 TOPS (INT4) of inference performance and 8GB of dedicated LPDDR4 memory, consuming just...
arXiv:2604.06287v1 Announce Type: new Abstract: Mathematical models and numerical simulations offer a non-invasive way to explore cardiovascular phenomena, providing access to quantities that cannot b
arXiv:2604.07815v1 Announce Type: new Abstract: Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse att
At AIE we are starting a new tradition of 'Hallway Track' talks - our selections of attendee-led and -voted lightning talks that couldn't fit within our 'normal' tracks but we still wanted to feature
arXiv:2604.06710v1 Announce Type: new Abstract: We present ATANT (Automated Test for Acceptance of Narrative Truth), an open evaluation framework for measuring continuity in AI systems: the ability to
arXiv:2604.02022v2 Announce Type: replace Abstract: Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions
arXiv:2604.08070v1 Announce Type: new Abstract: Darija, the Moroccan Arabic dialect, is rich in visual content yet lacks specialized Optical Character Recognition (OCR) tools. This paper introduces At
arXiv:2604.07967v1 Announce Type: new Abstract: Adversarial claim rewriting is widely used to test fact-checking systems, but standard metrics fail to capture truth-conditional consistency and often l
arXiv:2604.06416v1 Announce Type: cross Abstract: Although LLM context lengths have grown, there is evidence that their ability to integrate information across long-form texts has not kept pace. We ev
arXiv:2604.06266v1 Announce Type: cross Abstract: Software-Defined Networking (SDN) improves network flexibility but also increases the need for reliable and interpretable intrusion detection. Large L
arXiv:2509.23435v2 Announce Type: replace-cross Abstract: The creation of high-quality multimodal datasets remains fundamental for advancing role-playing capabilities in large language models (LLMs).
arXiv:2506.06975v5 Announce Type: replace-cross Abstract: As API access becomes a primary interface to large language models (LLMs), users often interact with black-box systems that offer little trans
arXiv:2508.07112v4 Announce Type: replace-cross Abstract: Lifting-based 3D human pose estimation infers 3D joints from 2D keypoints but generalizes poorly because (x,y) coordinates alone are an ill-
Vercel Sandbox now supports automatic persistence in beta: when a sandbox is stopped, the session shuts down but the filesystem is automatically snapshotted, and when resumed, a new session boots ...
arXiv:2604.06231v1 Announce Type: cross Abstract: Database systems incorporate an ever-growing number of functions in their kernels (a.k.a., database native functions) for scenarios like new applicati
arXiv:2505.20662v3 Announce Type: replace Abstract: Efficient reproduction of research papers is pivotal to accelerating scientific progress. However, the increasing complexity of proposed methods oft
arXiv:2604.07041v1 Announce Type: cross Abstract: Text-to-SQL is the task of translating natural language queries into executable SQL for a given database, enabling non-expert users to access structur
arXiv:2604.08540v1 Announce Type: cross Abstract: Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchma
llama.cpp release **b8740** (commit `e34f042`) is a build of the open-source C/C++ LLM inference engine focused on the change 'CUDA: fuse muls' (PR #21665), which optimizes CUDA performance by fusi...
llama.cpp **b8741** is an incremental build release of the open-source [llama.cpp](https://github.com/ggml-org/llama.cpp) project, which provides LLM inference in C/C++. It is one of many frequentl...
llama.cpp release **b8742** (commit `7b69125`) is a incremental build of the C/C++ LLM inference engine focused on a Vulkan backend enhancement: it adds Q1_0 quantization type support to `ggml-vulk...
llama.cpp release **b8744**, published on April 10, 2026, is a build of the ggml-org/llama.cpp C/C++ LLM inference engine. Its primary change enables the reasoning budget sampler for Gemma 4 by add...
llama.cpp release **b8746** was published on April 10, 2026 (commit `0893f50`) and consists of a single change: marking the `--split-mode tensor` option as experimental in the `--help` output (PR #...
llama.cpp release **b8747** is the latest build of the C/C++ LLM inference engine, published on April 10, 2026 (commit `fb38d6f`). Its primary change is a bug fix in the `common` layer that resolve...
The search results do not contain the specific changelog details for llama.cpp release **b8748**. The closest available data is for build b8747 (the latest at time of search), and no per-build note...
The search results do not contain specific changelog details for the exact `b8749` tag. Based on the available information about the llama.cpp project and its release cadence, here is a factual sum...
**llama.cpp release b8750** is a tagged build of [llama.cpp](https://github.com/ggml-org/llama.cpp), the open-source C/C++ inference engine for large language models maintained under the ggml-org G...
HappyHorse-1.0 is a pseudonymous AI video generation model that appeared on April 7, 2026, topping the Artificial Analysis Video Arena leaderboard in both text-to-video and image-to-video (no audio...
arXiv:2510.21366v3 Announce Type: replace Abstract: In this work, we propose a novel framework to enable diffusion models to adapt their generation quality based on real-time network bandwidth constra
arXiv:2601.15474v2 Announce Type: replace-cross Abstract: Graph neural network (GNN) have demonstrated exceptional performance in solving critical problems across diverse domains yet remain susceptibl
arXiv:2604.08138v1 Announce Type: new Abstract: A join is a set of manuscript fragments identified as originally emanating from the same manuscript. We study manuscript join retrieval: Given a query i
arXiv:2509.23310v3 Announce Type: replace Abstract: Deep learning-based techniques for the analysis of multimodal remote sensing data have become popular due to their ability to effectively integrate
Vercel has eliminated the $10 monthly base fee for Observability Plus for all customers, moving to a fully usage-based pricing model where users are only charged for the observability events they c...
arXiv:2510.03046v2 Announce Type: replace Abstract: Machine learning potentials (MLPs) have become essential for large-scale atomistic simulations, enabling ab initio-level accuracy with computational
arXiv:2604.06405v1 Announce Type: new Abstract: Data harmonization remains a major bottleneck for integrative analysis due to heterogeneity in schemas, value representations, and domain-specific conve
arXiv:2508.04691v2 Announce Type: replace-cross Abstract: As humans move toward collaborating with coordinated robot teams, understanding how these teams coordinate and fail is essential for building
arXiv:2601.05529v5 Announce Type: replace Abstract: High success rates on navigation-related tasks do not necessarily translate into reliable decision making by foundation models. To examine this gap,
arXiv:2604.08260v1 Announce Type: new Abstract: Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item r
In freeskiing and snowboarding, traditional video replay shows you what happened during a complex aerial maneuver, but it fails to explain the physics of how it was possible. At the speed of the sport
arXiv:2603.18019v2 Announce Type: replace Abstract: Do language model benchmarks actually measure what practitioners intend them to ? High-level metadata is too coarse to convey the granular reality o
arXiv:2604.06185v1 Announce Type: cross Abstract: Fulfilling user needs through Large Language Model multi-turn, multi-step tool-use is rarely a straightforward process. Real user interactions are inh
Best part? The spontaneous booth conversations with builders focused on turning AI ambition into production systems that scale. Open models are moving fast. The infrastructure around them is too. Grea
arXiv:2604.06674v1 Announce Type: cross Abstract: Meaning in Persian poetry is both historical and relational. Words persist through literary tradition while shifting their force through changing cons
arXiv:2604.06173v1 Announce Type: cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning. In statutory do
arXiv:2604.06201v1 Announce Type: cross Abstract: While most reading comprehension benchmarks for LLMs focus on factual information that can be answered by localizing specific textual evidence, many r
arXiv:2604.06373v1 Announce Type: cross Abstract: New generation of AI coding tools, including AI-powered IDEs equipped with agentic capabilities, can generate code within the context of the project.
arXiv:2604.07306v1 Announce Type: cross Abstract: Existing dynamic data pruning methods often fail under noisy-label settings, as they typically rely on per-sample loss as the ranking criterion. This
arXiv:2604.08038v1 Announce Type: new Abstract: In a real-world traffic scenario, varying-scale objects are usually distributed in a cluttered background, which poses great challenges to accurate dete
arXiv:2604.07740v1 Announce Type: new Abstract: In recent years, video-based person Re-Identification (ReID) has gained attention for its ability to leverage spatiotemporal cues to match individuals a
arXiv:2604.06738v1 Announce Type: cross Abstract: We study offline learning in KL-regularized two-player zero-sum games, where policies are optimized under a KL constraint to a fixed reference policy.
arXiv:2604.07749v1 Announce Type: new Abstract: Large language models (LLMs) can shift their answers under pressure in ways that reflect accommodation rather than reasoning. Prior work on sycophancy h
arXiv:2604.07763v1 Announce Type: new Abstract: As generative artificial intelligence evolves, deepfake attacks have escalated from single-modality manipulations to complex, multimodal threats. Existi
arXiv:2604.06820v1 Announce Type: new Abstract: Large language models (LLMs) can generate persuasive narratives at scale, raising concerns about their potential use in disinformation campaigns. Assess
arXiv:2604.07198v1 Announce Type: new Abstract: Emotion annotation is inherently subjective and cognitively demanding, producing signals that reflect diverse perceptions across annotators rather than
arXiv:2604.06727v1 Announce Type: new Abstract: Heterogeneity in time series data is more pronounced than in vision or language, as temporal dynamics vary substantially across domains and tasks. Exist
arXiv:2604.06349v1 Announce Type: cross Abstract: Generalizing from a single labeled source domain to unseen target domains, without access to any target data during training, remains a fundamental ch
arXiv:2604.06701v1 Announce Type: new Abstract: Autoencoders are widely used for dimensionality reduction, based on the assumption that high-dimensional data lies on low-dimensional manifolds. Regular
arXiv:2604.08111v1 Announce Type: cross Abstract: Machine unlearning enables models to selectively forget training data, driven by privacy regulations such as GDPR and CCPA. However, its fairness impl