Knowledge catalogue
arXiv:2605.17303v1 Announce Type: new Abstract: Recovering a dynamic 3D scene from a long monocular video is crucial for dense geometry, camera motion, and temporal correspondence to remain consistent
arXiv:2605.18739v1 Announce Type: new Abstract: We present LongLive-2.0, an NVFP4-based parallel infrastructure throughout the full training and inference workflow of long video generation, addressing
arXiv:2605.18565v1 Announce Type: cross Abstract: Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accura
arXiv:2605.17603v1 Announce Type: cross Abstract: High-resolution precipitation information is essential for climate impact assessment, yet global climate models remain too coarse to resolve key small
arXiv:2605.16343v1 Announce Type: cross Abstract: Looped language models (LoopLMs) improve parameter efficiency by recursively reusing Transformer blocks, enabling deeper computation under a fixed mod
arXiv:2605.18329v1 Announce Type: new Abstract: Ensemble disagreement is widely used as a proxy for epistemic uncertainty in medical image segmentation. In practice, many studies form ensembles via K-
arXiv:2605.16374v1 Announce Type: cross Abstract: Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has b
arXiv:2512.01030v3 Announce Type: replace Abstract: Recovering pixel-wise geometric properties from a single image is fundamentally ill-posed due to appearance ambiguity and non-injective mappings bet
arXiv:2605.17990v1 Announce Type: new Abstract: We present a real-time gaze tracking system that directly acquires task-relevant latent features using a fully passive optical encoder. Instead of formi
arXiv:2605.17329v1 Announce Type: cross Abstract: Guardrails are a critical safety layer for modern AI systems, but their operating regime is changing. As LLMs are deployed as customized assistants, s
arXiv:2508.06799v3 Announce Type: replace-cross Abstract: Digital Twins (DTs) offer powerful tools for managing complex infrastructure systems, but their effectiveness is often limited by challenges i
LTX 2.3's image-to-video (i2v) feature exhibits gradual video saturation and brightness degradation over extended generation sequences, though users have developed Python code aimed at recovering thes
arXiv:2601.14330v2 Announce Type: replace Abstract: Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, reveal
arXiv:2601.01685v2 Announce Type: replace-cross Abstract: As large language models (LLMs) transition to autonomous agents synthesizing real-time information, their reasoning capabilities introduce an
arXiv:2605.16375v1 Announce Type: new Abstract: Accurate air quality prediction is essential for public health, environmental monitoring, and industrial safety. However, most existing approaches rely
arXiv:2605.18572v1 Announce Type: new Abstract: Persuasive dialogue generation plays a vital role in decision-making, negotiation, counseling, and behavior change, yet it remains a challenging problem
arXiv:2509.18103v3 Announce Type: replace Abstract: Research on the distribution of prime numbers has revealed a dual character: deterministic in definition yet exhibiting statistical behavior reminis
arXiv:2605.16365v1 Announce Type: new Abstract: Early identification of individuals at elevated risk of Chlamydia trachomatis infection may enable optimal use of molecular testing in resource-aware sc
arXiv:2512.16085v2 Announce Type: replace-cross Abstract: Particulate composites underpin many solid-state chemical and electrochemical systems, where microstructural features such as multiphase bound
arXiv:2605.18253v1 Announce Type: cross Abstract: Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models
arXiv:2508.06670v2 Announce Type: replace-cross Abstract: By applying interpretable machine learning methods such as decision trees, we study how simple models can classify the Galois groups of Galois
arXiv:2605.17159v1 Announce Type: new Abstract: Document processing automation remains a critical challenge in enterprise environments, where traditional manual approaches are labor-intensive and erro
arXiv:2605.17478v1 Announce Type: new Abstract: Visual Geometry Grounded Transformers (VGGT) have set new benchmarks in high-fidelity 3D scene reconstruction. However, as the sequence length increases
arXiv:2605.18617v1 Announce Type: cross Abstract: Most existing vision-language manipulation research targets rigid robotic arms, whose fixed morphology limits adaptability in cluttered or confined sp
arXiv:2605.16301v1 Announce Type: cross Abstract: Single-turn benchmarks such as AnimalHarmBench (AHB) have established important baselines for measuring animal welfare alignment in large language mod
arXiv:2601.00360v3 Announce Type: replace-cross Abstract: As multi-agent AI systems become increasingly autonomous, evidence shows they can develop collusive strategies similar to those long observed
arXiv:2605.17120v1 Announce Type: new Abstract: arly identification of motor impairment in infancy relies on expert visual assessment of spontaneous movement, motivating the development of automated,
arXiv:2605.17640v1 Announce Type: cross Abstract: Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into cohere
arXiv:2605.17997v1 Announce Type: cross Abstract: Recently, residual reconstruction-based model quantization methods have achieved promising performance in low-bit post-training quantization (PTQ) by
arXiv:2605.18176v1 Announce Type: cross Abstract: This report presents MARS, short for Multimodal Agentic Reasoning with Source selection, our system for the CASTLE Challenge at EgoVis 2026. Participa
arXiv:2509.15357v2 Announce Type: replace Abstract: Diffusion models have achieved strong results in text-to-image generation, but important limitations remain as prompts become more structured and mu
arXiv:2603.06984v2 Announce Type: replace-cross Abstract: Many regulatory and analytic problems require that a prohibited variable influence a decision only through a designated allowable channel -- a
arXiv:2605.17431v1 Announce Type: cross Abstract: We propose MATE, a simple yet effective memory architecture for solving Contextual Markov Decision Processes (CMDPs), a family of MDPs parameterized b
arXiv:2010.15538v4 Announce Type: replace-cross Abstract: Gaussian processes are a versatile framework for learning unknown functions in a manner that permits one to utilize prior information about th
This post recommends an essay by Swyx on creating luck, which likely explores how deliberate actions, visibility, and strategic thinking can increase one's chances of encountering beneficial opportuni
arXiv:2605.06017v2 Announce Type: replace Abstract: Sequence-level evaluations in autoregressive Large Language Models (LLMs) rely on highly dependent token generation. Establishing tight concentratio
In a conversation between Matt Berman and Google CEO Sundar Pichai, Pichai confirmed that Google is experiencing greater demand for its services than its current computational capacity can handle. Thi
arXiv:2605.16716v1 Announce Type: cross Abstract: Text-to-video (T2V) generation has rapidly progressed in visual fidelity, yet its ability to faithfully represent multiple cultures within a single pr
arXiv:2605.17230v1 Announce Type: cross Abstract: Quantum error correction (QEC) is indispensable for realizing fault-tolerant quantum computation, yet its effectiveness hinges critically on the class
arXiv:2605.16290v1 Announce Type: cross Abstract: Predicting the difficulty of multiple-choice questions (MCQs) is important for effective assessment, yet current methods typically assume a unimodal s
arXiv:2605.16284v1 Announce Type: cross Abstract: Student use of Generative AI (GenAI) products in completing their classwork, with or without their professors' knowledge and/or approval, has resulted
arXiv:2605.17091v1 Announce Type: new Abstract: Scientific forecasting typically relies on direct state prediction, an approach that grows brittle under data scarcity, extended horizons, non-stationar
arXiv:2605.16468v1 Announce Type: cross Abstract: A central goal in understanding human vision is to uncover the visual features that drive neuronal activity. A growing body of work has used artificia
arXiv:2603.05308v2 Announce Type: replace-cross Abstract: Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language model
arXiv:2605.17436v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly proposed for clinical decision support, yet their reliability in real-world scenarios that require inte
arXiv:2605.16639v1 Announce Type: new Abstract: Multimodal clinical prediction faces three challenges: multiple foundation models (FMs) with complementary strengths per modality, pervasive missing mod
arXiv:2602.11130v2 Announce Type: replace-cross Abstract: Sparse point clouds are a common input modality for 3D surface reconstruction, including in safety-critical settings such as surgical navigati
arXiv:2605.16445v1 Announce Type: cross Abstract: Masked Diffusion Language Models MDLMs replace autoregressive generation with iterative demasking and their privacy properties are largely unstudied.
arXiv:2605.18652v1 Announce Type: new Abstract: Recent GUI agents have made substantial progress in visual grounding and action prediction, yet they remain brittle in long-horizon tasks that require m
arXiv:2605.17758v1 Announce Type: new Abstract: Synthetic data is widely used in healthcare to create datasets that are similar to original data but without the privacy concerns. Generating and evalua
arXiv:2601.21468v5 Announce Type: replace Abstract: Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memor
arXiv:2605.17365v1 Announce Type: new Abstract: Different from traditional text-to-image retrieval tasks, chat-based image retrieval allows the human-interactive system to iteratively clarify and refi
arXiv:2506.15588v2 Announce Type: replace Abstract: Differential privacy (DP) protects sensitive data during neural network training, but standard methods like DP-Adam suffer from high memory overhead
arXiv:2605.17539v1 Announce Type: new Abstract: Combinatorial optimization (CO) underlies decision-making from logistics to chip design, where infeasible solutions are operationally unusable and small
arXiv:2605.17444v1 Announce Type: cross Abstract: Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can op
arXiv:2602.12871v2 Announce Type: replace Abstract: Large language models (LLMs) have attracted growing interest as supportive tools for psychiatric assessment and clinical decision support. However,
arXiv:2510.10528v3 Announce Type: replace Abstract: Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this length
arXiv:2601.02353v3 Announce Type: replace Abstract: Farmers in remote areas need quick and reliable methods for identifying plant diseases, yet they often lack access to laboratories or high-performan
Meta Platforms Inc. is reportedly reassigning about 7,000 workers into new artificial intelligence roles as part of the broader restructuring that brings layoffs of roughly 8,000 staff into effect on
arXiv:2605.17292v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems have shown promise for solving complex tasks through agent collaboration. However, existing frameworks as