Knowledge catalogue
arXiv:2604.04415v2 Announce Type: replace Abstract: Human understanding of video dynamics is typically grounded in a structured mental representation of entities, actions, and temporal relations, rath
arXiv:2604.11637v1 Announce Type: new Abstract: 4D point cloud videos capture rich spatial and temporal dynamics of scenes which possess unique values in various 4D understanding tasks. However, most
arXiv:2506.18831v2 Announce Type: replace Abstract: Large Language Models employing extended chain-of-thought (CoT) reasoning often suffer from the overthinking phenomenon, generating excessive and re
arXiv:2604.03723v2 Announce Type: replace Abstract: Controlling both camera motion and object dynamics is essential for coherent and expressive video generation, yet current methods typically handle o
arXiv:2511.06101v3 Announce Type: replace-cross Abstract: Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored
arXiv:2508.02204v4 Announce Type: replace Abstract: Adept manipulation of articulated objects is essential for robots to operate successfully in human environments. Such manipulation requires both eff
arXiv:2604.10727v1 Announce Type: cross Abstract: Classical information-theoretic generalization bounds typically control the generalization gap through KL-based mutual information and therefore rely
arXiv:2509.04123v2 Announce Type: replace Abstract: Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods stru
arXiv:2604.10912v1 Announce Type: new Abstract: Medical image segmentation remains challenging due to limited fine-grained annotations, complex anatomical structures, and image degradation from noise,
arXiv:2604.10720v1 Announce Type: new Abstract: Artificial models that simulate how learners act and respond within educational systems are a promising tool for evaluating tutoring strategies and feed
arXiv:2507.22767v3 Announce Type: replace-cross Abstract: Obtaining human-readable symbolic formulas via genetic programming-based symbolic distillation of a deep neural network trained on a target da
arXiv:2604.11025v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) have begun to support Thinking with Images by invoking visual tools such as zooming and cropping during
arXiv:2604.09781v1 Announce Type: new Abstract: Vision-Language Models (VLMs) exhibit strong visual reasoning capabilities, yet they still struggle with 3D understanding. In particular, VLMs often fai
arXiv:2604.10261v1 Announce Type: new Abstract: Existing tool-use benchmarks for LLM agents are overwhelmingly linear: our analysis of six benchmarks shows 55 to 100% of instances are simple chains of
arXiv:2604.10577v1 Announce Type: cross Abstract: Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automat
arXiv:2504.12654v1 Announce Type: cross Abstract: This perspective paper examines a fundamental paradox in the relationship between professional expertise and artificial intelligence: as domain expert
arXiv:2604.11297v1 Announce Type: cross Abstract: Despite the success of reinforcement learning for large language models, a common failure mode is reduced sampling diversity, where the policy repeate
arXiv:2601.11496v2 Announce Type: replace-cross Abstract: The integration of AI agents into economic markets fundamentally alters the landscape of strategic interaction. We investigate the economic im
arXiv:2604.11309v1 Announce Type: cross Abstract: Large Language Models (LLMs) face prominent security risks from jailbreaking, a practice that manipulates models to bypass built-in security constrain
arXiv:2604.11435v1 Announce Type: cross Abstract: Character description generation is an important capability for narrative-focused applications such as summarization, story analysis, and character-dr
arXiv:2510.15552v3 Announce Type: replace-cross Abstract: Large language models (LLMs) still struggle with multi-hop reasoning over knowledge-graphs (KGs), and we identify a previously overlooked stru
arXiv:2604.02736v3 Announce Type: replace Abstract: Generating photorealistic 3D hand-object interactions (HOIs) from text is important for applications like robotic grasping and AR/VR content creatio
arXiv:2604.10788v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools durin
arXiv:2604.09692v1 Announce Type: new Abstract: Synthesizing realistic piano hand motions requires both precision and naturalness. Physics-based methods achieve precision but produce stiff motions; da
Nous Research hosted the Hermes Agent Jam event on Tuesday, April 14th at 4PM EST within their Discord server. The event featured presentations and a Q&A session with the Nous Research team, centered
arXiv:2604.09879v1 Announce Type: new Abstract: Deep neural networks for 3D point cloud understanding have achieved remarkable success in object classification and recognition, yet recent work shows t
arXiv:2604.10969v1 Announce Type: cross Abstract: To ensure energy efficiency and reliable operations, it is essential to monitor solar panels in generation plants to detect defects. It is quite labor
arXiv:2601.21078v3 Announce Type: replace Abstract: Temporal Action Localization (TAL) requires identifying both the boundaries and categories of actions in untrimmed videos. While vision-language mod
arXiv:2604.10009v1 Announce Type: cross Abstract: Automatic sleep staging is a multimodal learning problem involving heterogeneous physiological signals such as EEG and EOG, which often suffer from do
arXiv:2604.11077v1 Announce Type: new Abstract: Customer service chatbots are increasingly expected to serve not merely as reactive support tools for users, but as strategic interfaces for harvesting
arXiv:2604.10158v1 Announce Type: new Abstract: While modern transformer neural networks achieve grandmaster-level performance in chess and other reasoning tasks, their internal computation process re
arXiv:2604.09716v1 Announce Type: cross Abstract: Deep visual recognition models are usually trained and evaluated using metrics such as loss and accuracy. While these measures show whether a model is
arXiv:2604.11564v1 Announce Type: new Abstract: Single-image super-resolution has progressed from deep convolutional baselines to stronger Transformer and state-space architectures, yet the correspond
arXiv:2604.09850v1 Announce Type: new Abstract: Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a pass
arXiv:2604.10848v1 Announce Type: new Abstract: Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attenti
arXiv:2511.00413v4 Announce Type: replace Abstract: Agentic large language model (LLM) training often involves multi-turn interaction trajectories that branch into multiple execution paths due to conc
arXiv:2604.11522v1 Announce Type: new Abstract: Reinforcement learning for open-ended text generation is constrained by the lack of verifiable rewards, necessitating reliance on judge models that requ
arXiv:2505.17682v2 Announce Type: replace-cross Abstract: Predicting user behavior is essential for intelligent assistant services, yet deep learning models often struggle to capture long-tailed behav
arXiv:2604.10721v1 Announce Type: cross Abstract: Natural-language Guided Cross-view Geo-localization (NGCG) aims to retrieve geo-tagged satellite imagery using textual descriptions of ground scenes.
arXiv:2604.10056v1 Announce Type: new Abstract: Unsupervised optical flow methods typically lack reliable uncertainty estimation, limiting their robustness and interpretability. We propose U^{2}Flow,
arXiv:2604.10485v1 Announce Type: cross Abstract: Low-visibility scenarios, such as low-light conditions, pose significant challenges to human pose estimation due to the scarcity of annotated low-ligh
arXiv:2604.11014v1 Announce Type: new Abstract: Ultra-high-definition (UHD) video denoising requires simultaneously suppressing complex spatio-temporal degradations, preserving fine textures and chrom
arXiv:2502.04501v3 Announce Type: replace Abstract: Large language models achieve state-of-the-art performance but are increasingly costly to fine-tune. Prompt tuning is a parameter-efficient fine-tun
arXiv:2603.16446v3 Announce Type: replace Abstract: When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the
arXiv:2604.09608v1 Announce Type: new Abstract: While enterprises amass vast quantities of data, much of it remains chaotic and effectively dormant, preventing decision-making based on comprehensive i
arXiv:2604.11668v1 Announce Type: new Abstract: The growing availability of co-located geospatial data spanning aerial imagery, street-level views, elevation models, text, and geographic coordinates o
arXiv:2604.10952v1 Announce Type: new Abstract: Selecting prototypical examples from a source distribution to represent a target data distribution is a fundamental problem in machine learning. Existin
arXiv:2604.09948v1 Announce Type: new Abstract: Although hyperspectral image (HSI) classification is critical for supporting various environmental applications, it is a challenging task due to the spe
arXiv:2505.09591v3 Announce Type: replace-cross Abstract: Despite remarkable progress in recent years, Vision Language Models (VLMs) remain prone to overconfidence and hallucinations on tasks such as
arXiv:2604.10645v1 Announce Type: cross Abstract: There is a pressing need for better development methods and tools to keep up with the growing demand and increasing complexity of new software systems
arXiv:2604.10542v1 Announce Type: cross Abstract: Video-to-Audio (V2A) generation is essential for immersive multimedia experiences, yet its evaluation remains underexplored. Existing benchmarks typic
arXiv:2604.11138v1 Announce Type: cross Abstract: In-hand object reorientation requires precise estimation of the object pose to handle complex task dynamics. While RGB sensing offers rich semantic cu
arXiv:2506.14629v3 Announce Type: replace-cross Abstract: Mosquito-borne diseases pose a major global health risk, requiring early detection and proactive control of breeding sites to prevent outbreak
arXiv:2604.10500v1 Announce Type: new Abstract: Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation
arXiv:2604.10167v1 Announce Type: cross Abstract: Multi-vector models dominate Visual Document Retrieval (VDR) due to their fine-grained matching capabilities, but their high storage and computational
arXiv:2604.11671v1 Announce Type: cross Abstract: Accurate material recognition is a fundamental capability for intelligent perception systems to interact safely and effectively with the physical worl
arXiv:2603.22003v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models typically map visual observations and linguistic instructions directly to robotic control signals. This 'black-b
arXiv:2604.09558v1 Announce Type: cross Abstract: With the widening gap between compute and memory operation latencies, data movement optimizations have become increasingly important for DNN compilati
arXiv:2604.10809v1 Announce Type: new Abstract: Recent advancements in learning from human demonstration have shown promising results in addressing the scalability and high cost of data collection req
arXiv:2604.10343v1 Announce Type: new Abstract: We study the operation of community water systems, where pumps and valves must be scheduled to reliably meet water demands while minimizing energy consu