Knowledge catalogue
arXiv:2608.06310v1 Announce Type: cross Abstract: Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong
arXiv:2608.06259v1 Announce Type: new Abstract: Reaction yield prediction remains challenging because labeled data are scarce and reaction space is both combinatorially large and sparsely populated, l
arXiv:2608.05627v1 Announce Type: new Abstract: Training-free open-vocabulary segmentation remains limited by a missing inference abstraction. Frozen vision-language features are produced at patch lev
arXiv:2507.03631v4 Announce Type: replace Abstract: Extracting interpretable mathematical models from complex dynamical systems is difficult, especially for chaotic dynamics observed with noisy experi
arXiv:2608.05245v1 Announce Type: new Abstract: Reusable skills, which encapsulate the procedural knowledge required to solve real-world professional tasks, offer LLM-based agents a path toward self-e
arXiv:2608.05858v1 Announce Type: new Abstract: Accurate object detection in aerial and satellite imagery is dependent upon the bounding box representation. This is especially true for spatially orien
arXiv:2608.05604v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly act as agents whose procedural knowledge is stored in reusable skill packages and loaded at inference time.
arXiv:2608.05416v1 Announce Type: new Abstract: Can nonlinear dynamical systems be learned through a compact linear state-space representation, without directly solving a non-convex system-identificat
arXiv:2608.05703v1 Announce Type: new Abstract: Deploying autonomous multimodal agents in continuous, real-world environments requires them to ingest unbounded audio-visual streams and maintain hour-s
arXiv:2608.05656v1 Announce Type: cross Abstract: Safety risks of AI are becoming increasingly evident in human interactions with AI technologies. The prominent approaches to evaluating these risks fa
arXiv:2608.05785v1 Announce Type: cross Abstract: Multilingual text embedding models are commonly adapted using a single training objective across diverse tasks, despite different tasks requiring fund
Alibaba’s Qwen team announced the new Qwen‑3.8‑Max model and thanked users for extensive testing, noting its ability to provide highly detailed world observations. A community member highlighted that
arXiv:2608.05982v1 Announce Type: new Abstract: Inadequate target--disease linkage accounts for 40--50% of Phase~II efficacy failures, so anticipating which programmes will advance would let sponsors
arXiv:2608.06370v1 Announce Type: new Abstract: Tool use transforms LLMs into agents that act beyond their training data, and for code-capable models, programmatic tool calling extends this further by
arXiv:2608.06270v1 Announce Type: new Abstract: The 'thinking-with-images' paradigm equips multimodal LLMs with active visual operations such as crop-and-zoom. However, models using these operations o
arXiv:2608.06021v1 Announce Type: new Abstract: Effective Visual Localization (VL) requires a map of the environment that combines compactness for efficient scalability with robustness against visual
arXiv:2608.05616v1 Announce Type: new Abstract: Despite the remarkable progress of large vision language models (LVLMs), object hallucination remains a fundamental challenge that hinders their trustwo
arXiv:2608.06223v1 Announce Type: new Abstract: While deep learning models, particularly transformer-based architectures, have shown impressive performance in time series forecasting, the application
arXiv:2608.06331v1 Announce Type: cross Abstract: From natural-language query interfaces to automated report generation, data analysis tools need a description of the data: the real-world entities it
arXiv:2608.05729v1 Announce Type: new Abstract: As capabilities rapidly increase, AI agents can move from running inside one app to acting across a user's devices over time. Yet existing agent systems
arXiv:2608.05365v1 Announce Type: new Abstract: This paper presents an observation-only autonomy framework for Unmanned Underwater Vehicles (UUVs) navigation in dynamic underwater environments that in
arXiv:2608.05745v1 Announce Type: cross Abstract: Video Virtual Try-On (VVT) synthesizes a video of a person wearing a target garment while preserving identity, motion, and scene dynamics. Dominant ap
arXiv:2608.05671v1 Announce Type: new Abstract: Previous RGB-D semantic segmentation methods commonly employ dual encoders to separately process RGB and depth inputs, followed by dedicated modules for
arXiv:2504.13621v2 Announce Type: replace Abstract: Visual grounding associates textual descriptions with objects in an image. Conventional methods target third-person image inputs and named object qu
arXiv:2608.05776v1 Announce Type: new Abstract: Autoregressive continuation provides a natural path toward minute-scale audio-visual generation by repeatedly extending a short-window generator conditi
arXiv:2608.05792v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) is transforming Integrated Sensing and Communication (ISAC) from a function-oriented physical-layer technology into
arXiv:2608.05778v1 Announce Type: new Abstract: Prompt-side playbooks can improve tool-using language agents without retraining, but their portability beyond the source setting is unclear. We study fr
arXiv:2603.12617v2 Announce Type: replace-cross Abstract: Speculative decoding has emerged as a widely adopted paradigm for accelerating large language model inference, where a lightweight draft model
arXiv:2608.05810v1 Announce Type: new Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: p
arXiv:2608.05168v1 Announce Type: new Abstract: Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures arise from localiz
arXiv:2608.04215v1 Announce Type: cross Abstract: The growing diversity of code clone types, from syntactic copies to cross-language semantic clones to AI-generated duplicates, has created a fragmenta
arXiv:2608.04061v1 Announce Type: new Abstract: Utility poles are an essential part of the infrastructure used to support power distribution systems and other critical public services. Their regular i
arXiv:2608.04314v1 Announce Type: cross Abstract: Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can add
arXiv:2608.04190v1 Announce Type: new Abstract: Deploying pre-trained perception models in novel environments degrades their accuracy under distributional shift, and assembling them alone does not rec
arXiv:2608.04053v1 Announce Type: cross Abstract: Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous e
arXiv:2608.04065v1 Announce Type: cross Abstract: Vehicle-to-everything (V2X) systems increasingly incorporate large language models (LLMs) for semantic tasks such as message summarization, operator a
arXiv:2607.16060v2 Announce Type: replace Abstract: Artistic charts combine data visualization with expressive marks, textures, and typography, but they are difficult for image generators: an output i
arXiv:2608.04334v1 Announce Type: cross Abstract: Contemporary model-free reinforcement learning algorithms can achieve very high performance, but have low sample efficiency and are not robust to chan
arXiv:2606.14591v2 Announce Type: replace-cross Abstract: Recent advances in pretrained large audio-language models (LALMs) have demonstrated strong capabilities across speech, sound, and music. To ad
arXiv:2608.04454v1 Announce Type: new Abstract: Mixture-of-experts vision-language models (MoE-VLMs) increase model capacity with sparse expert activation, yet deployment requires storing the full exp
arXiv:2607.16868v2 Announce Type: replace Abstract: Large Language Models often produce confidently stated yet unreliable outputs, posing critical challenges for deployment in safety-sensitive applica
arXiv:2608.05104v1 Announce Type: new Abstract: Deep neural networks have shown impressive success in NLP tasks owing to their complex structure and huge number of edges. Achieving state-of-the-art pe
arXiv:2608.05042v1 Announce Type: new Abstract: Leveraging pre-trained vision-language models (VLMs) to construct vision-language-action (VLA) models has emerged as a promising paradigm for 3D robot m
arXiv:2608.04013v1 Announce Type: cross Abstract: Recent advances in Multimodal Emotion Recognition in Conversations (MERC) highlight its reliance on complete multimodal inputs. However, real-world da
arXiv:2608.04746v1 Announce Type: new Abstract: LLM agents that persist across sessions accumulate stored memories whose validity varies enormously by content type, yet existing memory architectures t
arXiv:2512.20661v2 Announce Type: replace Abstract: Transformer-based pre-trained language models (PLMs) excel in text classification but suffer from attention dilution and attention sink effects, for
arXiv:2511.19418v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual per
arXiv:2512.22969v2 Announce Type: replace Abstract: Conventional object detectors rely on cross-entropy classification, which can be vulnerable to class imbalance and label noise. We propose CLIP-Join
arXiv:2608.04396v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have driven significant progress in robotic manipulation, yet they fundamentally struggle with the vision-override p
arXiv:2608.04926v1 Announce Type: cross Abstract: As chart images, tabular data, and visualization code play increasingly important roles across diverse domains, cross-representation understanding acr
arXiv:2608.04778v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) incorporate governing equations into neural-network training and can approximate PDE solutions without requirin
arXiv:2608.04604v1 Announce Type: new Abstract: Source-free domain adaptation (SFDA) adapts a source-trained model to an unlabeled target domain without source data, a practical setting under privacy
arXiv:2608.04444v1 Announce Type: cross Abstract: Large language models (LLMs) often generate inaccurate answers due to their reliance on static internal knowledge. Retrieval-augmented generation (RAG
arXiv:2608.04622v1 Announce Type: new Abstract: AI agents have emerged as a powerful new paradigm in generative image synthesis, enabling systems to perform complex semantic reasoning rather than pass
arXiv:2608.04496v1 Announce Type: new Abstract: Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bottl
arXiv:2608.04677v1 Announce Type: new Abstract: Algorithmic recourse seeks to help individuals reverse unfavorable automated decisions by recommending actionable changes that achieve a desired outcome
arXiv:2608.04588v1 Announce Type: cross Abstract: Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing sy
arXiv:2608.04533v1 Announce Type: new Abstract: Part-level affordance grounding has advanced the localization of functional object regions associated with elemental actions. Extending this capability
arXiv:2608.04401v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models enable model scaling while maintaining low inference-time compute by activating only a subset of experts per token. Howe
arXiv:2608.04339v1 Announce Type: cross Abstract: Large language models are increasingly used for information seeking, yet semantically equivalent questions phrased in different ways can receive answe