Knowledge catalogue
arXiv:2604.12772v1 Announce Type: new Abstract: Changes in satellite imagery often occur over multiple time steps. Despite the emergence of bi-temporal change captioning datasets, there is a lack of m
arXiv:2505.17086v4 Announce Type: replace Abstract: Large Language Models (LLMs) equipped with modern Retrieval-Augmented Generation (RAG) systems often employ multi-turn interaction pipelines to inte
arXiv:2604.06812v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated impressive capabilities in long-form generation, yet their application is hindered by the hallucinati
ARC-AGI-3 is a new benchmark iteration designed so that any intelligent human applying genuine effort should achieve greater than 90% accuracy, maintaining the benchmark's core principle that tasks mu
arXiv:2604.12033v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook c
arXiv:2510.00919v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across diverse tasks, but their capacity for exper
arXiv:2604.12683v1 Announce Type: new Abstract: Current fMRI foundation models primarily rely on a limited range of brain states and mismatched pretraining tasks, restricting their ability to learn ge
arXiv:2604.11867v1 Announce Type: cross Abstract: We set out to train behavioral dispositions (self-verification, uncertainty acknowledgment, feedback integration) into small language models (0.6B to
arXiv:2604.12948v1 Announce Type: new Abstract: LLM agents with persistent memory store information as flat factual records, providing little context for temporal reasoning, change tracking, or cross-
arXiv:2604.11810v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, their immense number
arXiv:2512.19728v2 Announce Type: replace Abstract: Large language models (LLMs) continue to struggle with mathematical reasoning, and common post-training pipelines often reduce each generated soluti
arXiv:2604.12185v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enhances large language models by grounding outputs in retrieved knowledge. However, existing RAG methods including
arXiv:2604.12986v1 Announce Type: cross Abstract: Autonomous AI agents are rapidly transitioning from experimental tools to operational infrastructure, with projections that 80% of enterprise applicat
arXiv:2603.14634v3 Announce Type: replace Abstract: Robotics demands simulation that can reason about the diversity of real-world physical interactions, from rigid to deformable objects and fluids. Cu
arXiv:2604.13016v1 Announce Type: cross Abstract: On-policy distillation (OPD) has become a core technique in the post-training of large language models, yet its training dynamics remain poorly unders
arXiv:2604.12693v1 Announce Type: new Abstract: Deep learning models often achieve expert-level accuracy in medical image classification but suffer from a critical flaw: semantic incoherence. These hi
arXiv:2602.18109v2 Announce Type: replace Abstract: Real-time schedulers must reason about tight deadlines under strict compute budgets. We present TempoNet, a reinforcement learning scheduler that pa
arXiv:2512.03963v3 Announce Type: replace Abstract: Enhancing the temporal understanding of Multimodal Large Language Models (MLLMs) is essential for advancing long-form video analysis, enabling tasks
arXiv:2604.12610v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) mitigates hallucination in large language models (LLMs) by incorporating external knowledge during generation. Howe
arXiv:2510.20635v2 Announce Type: replace-cross Abstract: Curiosity serves as a pivotal conduit for human beings to discover and learn new knowledge. Recent advancements of large language models (LLMs
arXiv:2604.09676v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for enhancing reasoning in large language models (LLMs), yet scalable training is often hindered
arXiv:2510.03989v2 Announce Type: replace-cross Abstract: The Transformer architecture has revolutionized the field of sequence modeling and underpins the recent breakthroughs in large language models
arXiv:2604.11048v1 Announce Type: cross Abstract: Imbuing Large Language Models (LLMs) with specific personas is prevalent for tailoring interaction styles, yet the impact on underlying cognitive capa
arXiv:2604.05510v2 Announce Type: replace Abstract: Augmented reality (AR) has rapidly expanded over the past decade. As AR becomes increasingly integrated into daily life, its security and reliabilit
arXiv:2604.11483v1 Announce Type: new Abstract: Goal-directed molecular generation requires satisfying heterogeneous constraints such as protein--ligand compatibility and multi-objective drug-like pro
arXiv:2604.11632v1 Announce Type: new Abstract: We introduce CARTBENCH, a museum-grounded benchmark for evaluating vision-language models (VLMs) on Chinese artworks beyond short-form recognition and Q
arXiv:2604.10039v1 Announce Type: new Abstract: Vision--language models (VLMs) have achieved impressive performance on complex multimodal reasoning tasks, yet they still fail on simple grounding skill
arXiv:2604.09596v1 Announce Type: new Abstract: Dermatologic diseases impose a large and growing global burden, affecting billions and substantially reducing quality of life. While modern therapies ca
arXiv:2604.09666v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reason
arXiv:2510.11217v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models (LLMs) with external ret
arXiv:2604.11514v1 Announce Type: cross Abstract: This work addresses test output prediction, a key challenge in test case generation. To improve the reliability of predicted outputs by LLMs, prior ap
arXiv:2604.09599v1 Announce Type: cross Abstract: High-performance computing systems are complex machines whose behaviour is governed by the correct functioning of its many subsystems. Among these, th
arXiv:2510.05837v2 Announce Type: replace Abstract: Balancing exploration and exploitation remains a central challenge in reinforcement learning with verifiable rewards (RLVR) for large language model
arXiv:2503.16771v3 Announce Type: replace-cross Abstract: As Large Language Models for Code (LM4Code) become integral to software engineering, establishing trust in their output becomes critical. Howe
arXiv:2604.09741v1 Announce Type: cross Abstract: For large language models deployed through black-box APIs, recurring inference costs often exceed one-time training costs. This motivates composed age
arXiv:2502.19056v2 Announce Type: replace-cross Abstract: Fatigue modeling is essential for motion synthesis tasks to model human motions under fatigued conditions and biomechanical engineering applic
arXiv:2512.18073v2 Announce Type: replace Abstract: Multimodal LLMs (MLLMs) are capable of performing complex data analysis, visual question answering, generation, and reasoning tasks. However, their
arXiv:2604.09634v1 Announce Type: cross Abstract: Most AI literacy courses for non-technical undergraduates emphasize conceptual breadth over technical depth. This paper describes UNIV 182, a prerequi
arXiv:2604.09711v1 Announce Type: cross Abstract: Multimodal fake news detection (MFND) aims to verify news credibility by jointly exploiting textual and visual evidence. However, real-world news diss
arXiv:2509.21042v3 Announce Type: replace Abstract: Causal self-attention provides positional information to Transformer decoders. Prior work has shown that stacks of causal self-attention layers alon
arXiv:2512.20136v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has recently been extended to multimodal settings, connecting multimodal large language models (MLLMs) wi
arXiv:2604.10169v1 Announce Type: new Abstract: Trajectory prediction remains a critical yet challenging component in autonomous driving systems, requiring sophisticated reasoning capabilities while m
arXiv:2602.05467v2 Announce Type: replace-cross Abstract: Visual Language Navigation (VLN) is one of the fundamental capabilities for embodied intelligence and a critical challenge that urgently needs
arXiv:2604.11666v1 Announce Type: cross Abstract: As large language models (LLMs) become the engine behind conversational systems, their ability to reason about the intentions and states of their dial
arXiv:2602.03402v3 Announce Type: replace Abstract: Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerabl
arXiv:2604.10929v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) provide robots with contextual reasoning abilities to comprehend human instructions. Yet, current LLM-en
Over 80% of enterprise data lives in unstructured form — PDFs, emails, reports, regulatory filings. Most of the time, such sources contain critical business information, yet they remain difficult to a
arXiv:2604.09749v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) frequently hallucinate objects that are absent from the visual input, often because attention during decoding i
arXiv:2604.10734v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges
arXiv:2510.07972v3 Announce Type: replace Abstract: Query-product relevance prediction is vital for AI-driven e-commerce, yet current LLM-based approaches face a dilemma: SFT and DPO struggle with lon
arXiv:2604.10674v1 Announce Type: cross Abstract: Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited b
arXiv:2604.09614v1 Announce Type: new Abstract: This paper develops a measure-theoretic framework establishing when and how a possibilistic representation of incomplete knowledge contracts into a prob
Francois Chollet argues that memorization and knowledge function as a cache for previously completed cognitive work, allowing it to be reused efficiently rather than recomputed. The purpose of storing
arXiv:2603.27960v2 Announce Type: replace-cross Abstract: Although Large Vision Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, their scalability and deployment
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:2604.10245v1 Announce Type: new Abstract: Registration between preoperative CT and intraoperative laparoscopic video plays a crucial role in augmented reality (AR) guidance for minimally invasiv
arXiv:2604.10990v1 Announce Type: cross Abstract: Scientific claim verification, the task of determining whether claims are entailed by scientific evidence, is fundamental to establishing discoveries
arXiv:2604.09537v1 Announce Type: cross Abstract: Evidence-grounded reasoning requires more than attaching retrieved text to a prediction: a model should make decisions that depend on whether the prov
arXiv:2604.09367v1 Announce Type: new Abstract: Ancient inscriptions, as repositories of cultural memory, have suffered from centuries of environmental and human-induced degradation. Restoring their i
arXiv:2604.08708v1 Announce Type: cross Abstract: While Large Language Model-based Multi-Agent Systems (MAS) consistently outperform single-agent systems on complex tasks, their intricate interactions