Knowledge catalogue
arXiv:2606.08420v1 Announce Type: new Abstract: Vision-language models (VLMs) pretrained on large-scale image-text pairs demonstrate strong image-level understanding, but are primarily optimized for g
arXiv:2606.08327v1 Announce Type: cross Abstract: Standard transformers apply self-attention uniformly at every layer and token, regardless of whether the input requires dynamic cross-token interactio
arXiv:2603.13431v3 Announce Type: replace-cross Abstract: Computational antibody design has seen rapid methodological progress, with dozens of deep generative methods proposed in the past three years,
arXiv:2606.08959v1 Announce Type: new Abstract: We introduce ChinaHeritaQA, a multimodal benchmark dataset for evaluating the cultural reasoning abilities of vision-language models (VLMs) on UNESCO Wo
arXiv:2606.08864v1 Announce Type: new Abstract: The rapid adoption of diffusion and large-scale generative models has made it increasingly challenging to distinguish synthetic imagery from real photog
arXiv:2606.07962v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in open-world reasoning and understanding. Howe
arXiv:2606.09639v1 Announce Type: new Abstract: The fidelity and structural diversity of training datasets fundamentally determine the capabilities of video generation models. While commercial systems
arXiv:2606.08169v1 Announce Type: cross Abstract: Enabling robots to understand and execute tasks from natural language commands while maintaining data efficiency remains challenging. Foundation model
arXiv:2606.08826v1 Announce Type: new Abstract: Image data regarding galactic morphology is expected to increase both in quantity and quality for the next foreseeable years; thus it is important to ex
arXiv:2606.09180v1 Announce Type: new Abstract: We present our submission to the CVPR 2026 Argoverse 2 Scenario Mining Challenge. Our system uses a four-stage pipeline: (1) autonomous code generation
arXiv:2606.09138v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving
arXiv:2508.05950v2 Announce Type: replace-cross Abstract: We propose CLONE, a 3DGS-based Closed-Loop differentiable Optimization framework for single-image Normal Estimation. The core idea is to const
arXiv:2606.09520v1 Announce Type: cross Abstract: Can a general-purpose large language model design molecules with the precision of a seasoned chemist? Current LLM-based frameworks answer this questio
arXiv:2606.08168v1 Announce Type: cross Abstract: Leading commercial endpoint detection and response (EDR) products have shifted from operator-configured rule sets to multi-component systems where aut
arXiv:2606.09607v1 Announce Type: cross Abstract: Interpretability increasingly treats groups of components, not individual units, as the basic object, and proposes to find them by clustering co-activ
arXiv:2509.25004v2 Announce Type: replace Abstract: Online reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning abilities of large languag
arXiv:2512.13869v3 Announce Type: replace Abstract: Training object detectors demands extensive, task-specific annotations, yet this requirement becomes impractical in UAV-based human detection due to
arXiv:2606.09577v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as code generators, where silently wrong programs pose real safety and reliability risks. Relia
arXiv:2603.04177v2 Announce Type: replace-cross Abstract: LLM coding agents can generate working code, but their solutions often accumulate complexity, duplication, and architectural debt. Human devel
arXiv:2512.16349v2 Announce Type: replace-cross Abstract: We propose a collaborative edge-to-server inference framework for vision-language models (VLMs) that reduces communication cost while maintain
arXiv:2606.09751v1 Announce Type: new Abstract: Foundation models are moving from response generation into operational roles. They plan across steps, call tools, request human input, coordinate with o
arXiv:2410.05662v4 Announce Type: replace Abstract: Most federated learning (FL) approaches assume a fixed device set. However, real-world scenarios often involve devices dynamically joining or leavin
arXiv:2606.07522v1 Announce Type: cross Abstract: We propose an unsupervised method of resolving slang, unique entities, and folklore from online communities by isolating words in the lexicon that hav
arXiv:2601.20503v2 Announce Type: replace-cross Abstract: White matter hyperintensities (WMH) and ischaemic stroke lesions (ISL) are key imaging biomarkers of cerebral small vessel disease (SVD) detec
arXiv:2604.02056v2 Announce Type: replace Abstract: Missing modalities in multimodal sensing cause not only information loss but also a fusion-interface mismatch: a fusion head trained on a canonical
arXiv:2412.19754v4 Announce Type: replace-cross Abstract: Artificial Intelligence (AI) is transforming the nature of work, yet there is limited empirical evidence on how it affects demand for human sk
arXiv:2606.09118v1 Announce Type: new Abstract: As LLM capabilities advance rapidly, the evaluation methods used to assess them increasingly lag behind. Traditional benchmarks relied on programmatic v
arXiv:2603.22473v2 Announce Type: replace-cross Abstract: Hybrid language models combine softmax attention with linear-time sequence mechanisms such as state-space or linear-attention layers, but the
arXiv:2606.08727v1 Announce Type: cross Abstract: Many classically studied function classes are known to be approximated optimally by superpositional methods, i.e. with approximants constructed as the
arXiv:2606.09331v1 Announce Type: cross Abstract: Omni-modal retrieval promises a single embedding space for text, image, video, document, and audio inputs, but building such a unified retriever is di
arXiv:2606.07543v1 Announce Type: cross Abstract: Generative AI (GenAI) is transforming workplaces at a rapid pace. This disproportionately affects vulnerable communities, including older workers (OWs
arXiv:2602.17911v3 Announce Type: replace-cross Abstract: Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is
arXiv:2601.07013v2 Announce Type: replace-cross Abstract: Traditional filtering algorithms for state estimation -- such as classical Kalman filtering, unscented Kalman filtering, and particle filters
arXiv:2606.08113v1 Announce Type: new Abstract: A small Wasserstein distance does not certify that a transformation is admissible. In evidence-constrained, semantic, causal, physical, monotone, or ris
arXiv:2606.08702v1 Announce Type: new Abstract: Recent advances have improved the adaptive capabilities of LLM-based multi-agent systems (MAS) through memory-, skill-, and learning-based approaches, y
arXiv:2606.07564v1 Announce Type: cross Abstract: This report explores detector design considerations for the Future Circular Collider in its electron-positron mode (FCC-ee) through an extended dialog
arXiv:2606.08088v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has recently become a key paradigm for improving the reasoning abilities of Large Language Models
arXiv:2606.08158v1 Announce Type: cross Abstract: Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors. Prior work largely
arXiv:2606.09623v1 Announce Type: new Abstract: When running marketing campaigns, retailers must decide which products to promote and which users to target. These decisions are inherently coupled: eff
arXiv:2606.08100v1 Announce Type: new Abstract: Multimodal DeltaDelta G predictors integrating protein language models with inverse-folding representations achieve strong in-distribution accuracy on t
arXiv:2606.08251v1 Announce Type: cross Abstract: Bold projections that artificial intelligence will accelerate scientific discovery have raced ahead of evidence from working scientists, and the field
arXiv:2606.09419v1 Announce Type: cross Abstract: Artificial intelligence is rapidly advancing materials characterization, yet most applications in electron microscopy rely solely on image contrast, o
arXiv:2606.09084v1 Announce Type: cross Abstract: Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.g., workspace files or logs). Consequently, jailbreak
arXiv:2603.09995v2 Announce Type: replace-cross Abstract: Behavioral interview evaluation using large language models presents unique challenges that require structured assessment, realistic interview
arXiv:2606.09090v1 Announce Type: cross Abstract: Developers increasingly provide AI coding assistants with persistent context through configuration files such as CLAUDE.md, AGENTS.md, and .cursorrule
arXiv:2606.09495v1 Announce Type: new Abstract: Modern object detectors achieve strong performance on standard benchmarks, yet their robustness to contextual variation remains insufficiently understoo
arXiv:2606.08102v1 Announce Type: cross Abstract: Multi-quadruped coordination has attracted increasing attention due to its enhanced payload capacity, broader contact coverage, and improved adaptabil
arXiv:2606.08810v1 Announce Type: cross Abstract: Gaussian-corrupted sentence embeddings have no direct linguistic interpretation, yet continuous diffusion language models can generate fluent text fro
arXiv:2504.12556v2 Announce Type: replace Abstract: The elliptical shape prior information plays a vital role in improving the accuracy of image segmentation for specific tasks in medical and natural
arXiv:2606.07904v1 Announce Type: new Abstract: Tool-augmented large language model agents increasingly rely on external APIs, but standard tool schemas describe how to call a tool, not when the tool
arXiv:2606.07770v1 Announce Type: new Abstract: Self-supervised methods that learn representations and predict dynamics fully in the latent space, such as JEPA, have been shown to confuse slowly varyi
arXiv:2606.07604v1 Announce Type: cross Abstract: Analyzing attention weights has become a standard approach for interpreting the information flow of Large Language Models (LLMs). However, this approa
arXiv:2507.01598v5 Announce Type: replace Abstract: Muon, a recently proposed optimizer that leverages the inherent matrix structure of neural network parameters, has demonstrated strong empirical per
arXiv:2606.08584v1 Announce Type: new Abstract: Sparse coding provides a principled framework for signal representation by expressing an input as a linear combination of only a small number of basis f
arXiv:2505.03528v2 Announce Type: replace Abstract: Cooperative perception, leveraging shared information from multiple vehicles via vehicle-to-vehicle (V2V) communication, plays a vital role in auton
arXiv:2606.08064v1 Announce Type: new Abstract: Humans exhibit remarkable motor agility, enabling a wide range of dynamic skills such as running and jumping, which highlights the great potential of hu
arXiv:2606.09409v1 Announce Type: new Abstract: Pairwise comparisons combined with aggregation methods like Elo have become central to evaluating generative models, yet concerns remain that they rewar
arXiv:2511.11041v2 Announce Type: replace-cross Abstract: We find that current sentence-embedding models produce outputs with a consistent bias: every embedding e decomposes as ilde e + mu, where the
arXiv:2606.09672v1 Announce Type: new Abstract: Ask a pretrained biomedical language model whether 'cortisol 28 ug/dL' and 'stock-market volatility' are related, and it returns a cosine similarity of
arXiv:2505.13225v2 Announce Type: replace Abstract: Neural network pruning aims to compress models for efficient deployment, yet two fundamental challenges remain. First, many methods rely on per-comp