Knowledge catalogue
arXiv:2607.17486v2 Announce Type: replace-cross Abstract: As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks i
arXiv:2608.28978v1 Announce Type: new Abstract: Knowledge graphs have been proposed as a structured alternative to flat retrieval-augmented generation for long-term agent memory, on the assumption tha
arXiv:2608.28647v1 Announce Type: new Abstract: Target-only post-training can improve performance in a specialized domain while degrading behaviors that a general-purpose base model acquired before ad
arXiv:2608.30785v1 Announce Type: new Abstract: Production agent skills are directory bundles, not isolated prompts. The root is loaded at activation; references, schemas, scripts, assets, and nested
arXiv:2607.18642v2 Announce Type: replace Abstract: Mined code corpora are abundant but uncontrolled: a snippet's semantics, surface 'messiness,' and difficulty are whatever the wild contained; there
arXiv:2608.28708v1 Announce Type: cross Abstract: Prospective silent trials provide an important bridge between retrospective validation of artificial intelligence (AI) models and their use in clinica
arXiv:2603.11842v2 Announce Type: replace-cross Abstract: The post-ChatGPT surge has rapidly reframed IS research and practice. As organizations and society grapple with GenAI adoption, a body of seco
arXiv:2603.02465v2 Announce Type: replace-cross Abstract: Machine learning-based wildfire detection has advanced significantly using deep learning models trained on large wildfire image and video data
arXiv:2608.30769v1 Announce Type: new Abstract: LLM training is increasingly vulnerable to silent data corruption (SDC), yet existing protection methods largely treat Transformer computations uniforml
arXiv:2608.28062v2 Announce Type: replace Abstract: Multimodal search agents extend parametric knowledge with newly emerging and long-tail evidence from the open web. Yet many existing agentic search
arXiv:2608.31068v1 Announce Type: new Abstract: When a large language model fails a reasoning task, it is often assumed to lack the underlying capability. However, this conflates a genuine absence of
arXiv:2608.28020v1 Announce Type: new Abstract: Underwater 3D reconstruction faithfully reproduces the color shifts and visibility loss of captured views, while physical inversion may leave estimation
arXiv:2401.09940v2 Announce Type: replace Abstract: Expected Goals (xG) has emerged as a popular tool for evaluating finishing skill in soccer analytics. It involves comparing a player's cumulative xG
arXiv:2509.22737v3 Announce Type: replace Abstract: Visual comparison reasoning is a fundamental capability of vision-language models (VLMs), covering judgments of object quantity, geometric dimension
arXiv:2608.28316v1 Announce Type: new Abstract: Static importance scores compress visual evidence into a single ranking, but the value of remaining evidence can change after one cue has been observed.
arXiv:2608.27634v1 Announce Type: cross Abstract: Nearest neighbor classification relies fundamentally on how locality is defined, yet conventional k-NN imposes the same neighborhood cardinality throu
arXiv:2608.28080v1 Announce Type: new Abstract: Image-conditioned 3D generation has advanced rapidly, yet existing evaluation protocols largely judge rendered-view plausibility and semantic alignment,
arXiv:2608.27513v1 Announce Type: new Abstract: Softmax attention stores key and value vectors for every preceding token, causing inference memory to grow with sequence length. Recent language models
arXiv:2608.27922v1 Announce Type: new Abstract: Autoregressive video diffusion models enable streaming generation through sliding-window attention, but each generated block is conditioned on previousl
arXiv:2608.28237v1 Announce Type: new Abstract: Predictive Process Monitoring (PPM) models are increasingly deployed in dynamic environments where concept drift causes the underlying process distribut
arXiv:2509.26536v3 Announce Type: replace Abstract: We introduce OceanGym, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding r
arXiv:2608.27512v1 Announce Type: cross Abstract: Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision
arXiv:2608.27529v1 Announce Type: new Abstract: Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online under bounded memory and computation.
arXiv:2509.19212v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet their ability to make context-aware safety decisi
arXiv:2608.28279v1 Announce Type: new Abstract: Multimodal lifelong navigation requires an agent to autonomously explore unseen environments while sequentially completing navigation tasks specified by
arXiv:2608.26236v1 Announce Type: new Abstract: We present a six-stage framework for auditing the reproducibility of scientific claims across a research literature within the computer science domain,
arXiv:2608.27169v1 Announce Type: new Abstract: Ancient Chinese artifact text recognition is fundamental to heritage digitization, and benchmarks for ancient texts are essential for evaluating current
arXiv:2607.18064v2 Announce Type: replace-cross Abstract: Coding agents can now be left alone to improve software against a score. In this pattern--recently popularized as 'autoresearch'--the agent re
arXiv:2608.27268v1 Announce Type: new Abstract: Although Large language models (LLMs) mediate access to knowledge and computational assistance, their capabilities should benefit vulnerable groups in t
arXiv:2608.26870v1 Announce Type: new Abstract: Weak signals are early, low-visibility indicators that precede significant changes before those changes become established. Existing detection methods,
arXiv:2608.27278v1 Announce Type: cross Abstract: Whole-slide images (WSIs) are central to computational pathology but are prohibitively large, making patch-based processing the practical unit for fou
arXiv:2607.15439v2 Announce Type: replace Abstract: Our previous ARC-AGI-3 agent bundled executable world modeling, prompted simplification, and exact replay verification, leaving their individual con
arXiv:2608.26546v1 Announce Type: new Abstract: Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings. However, existing benchmarks typically sepa
arXiv:2608.27072v1 Announce Type: cross Abstract: A core question in decision-making for agents is whether the relative priorities of competing lower-level objectives can be determined by emotional pr
arXiv:2604.02324v2 Announce Type: replace-cross Abstract: Language models (LMs) are increasingly extended with new learnable vocabulary tokens for domain-specific tasks, such as Semantic-ID tokens in
arXiv:2608.27102v1 Announce Type: new Abstract: Large Language Models (LLMs) operate in hospitals, courtrooms, banks, and public service desks, where fluent, confident outputs are treated as authorita
arXiv:2608.26714v1 Announce Type: cross Abstract: Diffusion-based Video Virtual Try-On (VVT) achieves high visual fidelity through bidirectional spatio-temporal modeling, but complete-clip dependence
arXiv:2608.26161v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable capabilities in reasoning and decision-making, high-fidelity probabilistic sampling remai
arXiv:2608.26222v1 Announce Type: cross Abstract: Safety evaluation is critical for assessing whether aligned Large Language Models (LLMs) remain robust against jailbreak attacks. Existing automated t
arXiv:2608.26866v1 Announce Type: new Abstract: Many multimodal tasks depend on how visual elements are ordered and composed, not only on recognizing them in isolation. Internet memes are a compact ca
arXiv:2608.27085v1 Announce Type: new Abstract: We study the problem of decentralized, self-organized task sharing for a swarm of heterogeneous robots that collaborate in transportation or other objec
arXiv:2608.26530v1 Announce Type: new Abstract: Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience
arXiv:2608.26334v1 Announce Type: new Abstract: Automated theorem proving offers a natural foundation for recursive self-improvement in scientific discovery. However, existing neural provers do not fu
arXiv:2608.27328v1 Announce Type: new Abstract: High similarity between first-visit and return frames does not necessarily show that a video world model remembered the scene; the intervening rollout m
arXiv:2608.26739v1 Announce Type: new Abstract: Accurate trajectory tracking in cable-driven lower-limb rehabilitation robots is challenging because model uncertainty, external disturbances, joint con
arXiv:2608.26214v1 Announce Type: new Abstract: Surgical video data provides the primary training resource for models of intraoperative perception, surgical workflow understanding, and robotic decisio
arXiv:2608.26449v1 Announce Type: new Abstract: Byte-level BPE tokenizers that use the HuggingFace ByteLevel pre-tokenizer inherit GPT-2's word regex, where a word is defined as p{L}+, one or more Uni
arXiv:2608.27146v1 Announce Type: new Abstract: Tool-augmented LLM agents must rely on untrusted runtime Observations to complete open-ended tasks; however, when tool outputs no longer merely provide
arXiv:2608.25956v1 Announce Type: new Abstract: Current world action models (WAMs) typically operate on 2D visual data. These models can achieve exceptional visual quality, but they lack explicit spat
arXiv:2608.26008v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to jailbreak attacks that exploit techniques such as role-playing, obfuscation, code transformation, an
arXiv:2608.25710v1 Announce Type: new Abstract: Data augmentation is a standard component of modern semantic segmentation pipelines, but most augmentation techniques allocate transformations uniformly
arXiv:2608.24988v1 Announce Type: new Abstract: Activation steering can be embedded directly into a language model's weights, shaping behaviour without inference-time intervention and offering a way t
arXiv:2608.25659v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies have advanced language-conditioned robotic manipulation, yet action-imitation objectives provide only weak supervi
arXiv:2507.04167v2 Announce Type: replace Abstract: Rising labor costs and narrow treatment windows have made teleoperated robots a proposed tool for vineyard scouting and treatment, but simulation-ba
arXiv:2607.14480v3 Announce Type: replace Abstract: LLM evaluators (trained reward models and prompted LLM-as-a-Judge) are routinely validated via pairwise accuracy. In a multilingual setting, this op
arXiv:2608.25319v1 Announce Type: cross Abstract: UAV displacement attacks have traditionally relied on spoofing sensors that directly report position or translational motion, such as GNSS and optical
arXiv:2608.25990v1 Announce Type: new Abstract: Orthogonal optimisers such as Muon can substantially accelerate large language model pretraining relative to Adam, yet the mechanism remains incompletel
arXiv:2608.26067v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art models such as pi0.5 operate under a sin
arXiv:2608.24966v1 Announce Type: new Abstract: Vision-language models such as LLaVA-1.5-7B often hallucinate objects absent from the image when generating captions. We ask whether an interpretability
arXiv:2603.03297v2 Announce Type: replace Abstract: Test-time training (TTT) adapts large language models (LLMs) during inference using only unlabeled test inputs. Existing methods, however, face two