Knowledge catalogue
arXiv:2610.01282v1 Announce Type: new Abstract: The rapid evolution of Intelligent Transportation Systems and Logistics (ITS&L) has become a cornerstone of the modern social economy, relying heavily o
arXiv:2609.38411v1 Announce Type: new Abstract: Leading AI developers have reported agents acting beyond their approved limits, which a United Nations panel described as an early warning of loss of hu
arXiv:2609.39025v1 Announce Type: new Abstract: Fairness assessment in algorithmic decisions that affect individuals, such as credit scoring, often relies on parity measures calculated at the aggregat
arXiv:2505.14717v2 Announce Type: replace-cross Abstract: Scientific machine learning uses simulation data to train surrogate models for fast physical-field prediction across geometries. Local shape e
arXiv:2609.38444v1 Announce Type: new Abstract: Text- and image-conditioned world generators can create visually rich 3D environments, yet these worlds often remain silent or rely on soundtracks synth
arXiv:2609.39360v1 Announce Type: new Abstract: Despite recent progress in autoresearch, applying it to practical operations research problems, typically formulated as NP-hard mixed-integer linear or
arXiv:2609.39813v1 Announce Type: new Abstract: Low-precision training rounds tensors that the backward pass reads again, often for several gradients; each use can read the forward's rounded value, th
arXiv:2609.39139v1 Announce Type: new Abstract: Adaptive RAG uses signals such as confidence, relevance, support, and retrieval quality to decide when to search or correct evidence. In multi-step retr
arXiv:2609.40117v1 Announce Type: new Abstract: Time-series forecasting models achieve strong benchmark performance but exhibit severe systematic bias in industrial deployments. This train--deploy gap
arXiv:2609.38660v1 Announce Type: cross Abstract: Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent
arXiv:2609.38483v1 Announce Type: new Abstract: Indirect manipulation of deep-seated deformable anatomy inaccessible to the robot is challenging in robot-assisted minimally invasive surgery (RAMIS) be
arXiv:2609.39738v1 Announce Type: new Abstract: Learning to generate machining process plans and toolpaths from B-rep CAD requires coupling discrete operation decisions with continuous tool motion as
arXiv:2609.40324v1 Announce Type: new Abstract: We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong m
arXiv:2609.38684v1 Announce Type: new Abstract: Knowledge-intensive language-model systems typically represent external knowledge as text chunks or static graphs, with limited support for concept evol
arXiv:2601.22028v2 Announce Type: replace Abstract: Most LLM unlearning methods aim to approximate retrain-from-scratch behaviors with minimal distribution shift, often via alignment-style objectives
arXiv:2609.39050v1 Announce Type: cross Abstract: As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has ex
arXiv:2601.21857v2 Announce Type: replace Abstract: We revisit diffusion-based generation for structured visual content and identify a fundamental limitation of existing approaches: foreground preserv
arXiv:2609.39190v1 Announce Type: new Abstract: A deep classifier is defined not only by the decision it produces, but also by the sequence of transformations through which that decision is formed. Tr
arXiv:2609.38437v1 Announce Type: new Abstract: Teleoperation systems are tuned for channel fidelity, while whether the operator experiences the device as part of the body, the Sense of Embodiment (So
arXiv:2609.38758v1 Announce Type: new Abstract: Referring Video Object Segmentation (RVOS) aims to produce a pixel-accurate mask sequence for an object specified by natural language. Sa2VA combines a
arXiv:2609.39786v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly combined with knowledge graphs (KGs) to ground reasoning in structured evidence. However, most LLM-based K
arXiv:2609.38552v1 Announce Type: cross Abstract: Public institutions increasingly procure AI systems whose design they cannot inspect or change. In higher education, proprietary Early Warning Systems
arXiv:2609.39279v1 Announce Type: cross Abstract: Machine unlearning has emerged as a crucial mechanism for removing hazardous knowledge and enforcing safety alignment in Large Language Models (LLMs).
arXiv:2609.39837v1 Announce Type: new Abstract: Policy mirror descent (PMD) enjoys fast convergence in regularized Markov decision processes (MDPs), but existing guarantees often rely on exact or incr
arXiv:2509.03122v5 Announce Type: replace-cross Abstract: Reliable model fingerprints are essential for protecting large language models (LLMs) against unauthorized redistribution and commercial misus
arXiv:2609.39648v1 Announce Type: cross Abstract: Diffusion models are typically viewed as stochastic processes that transform noise into data. We take a complementary perspective: a diffusion model d
arXiv:2609.38911v1 Announce Type: new Abstract: Learning must acquire new capabilities while preserving both prior responsibilities and the capacity to learn again. We introduce Generalized Residual C
arXiv:2511.10936v3 Announce Type: replace-cross Abstract: Graph unlearning (GU) has emerged as a promising solution to comply with 'the right to be forgotten' regulations by enabling the removal of se
arXiv:2609.39794v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong promise for general-purpose robotic manipulation, yet adapting them to new tasks and domains remai
arXiv:2609.39261v1 Announce Type: new Abstract: Decision-focused learning (DFL) trains predictors through downstream objectives, but a different loss need not provide an independent parameter-update d
arXiv:2609.38764v1 Announce Type: new Abstract: Language models are typically pretrained from random initialization. Recent work challenges this convention, showing that a brief warm-up on abstract, a
arXiv:2604.08454v2 Announce Type: replace Abstract: Large language models are increasingly deployed in high-stakes domains, where confident yet incorrect inferences may cause severe real-world harm, b
arXiv:2609.39882v1 Announce Type: new Abstract: Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-t
arXiv:2609.39018v1 Announce Type: cross Abstract: Frontier models can control robots, but reasoning through every reach, grasp, and retreat makes manipulation slow and token-intensive. We revisit code
arXiv:2609.40195v1 Announce Type: cross Abstract: Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanni
arXiv:2609.39596v1 Announce Type: new Abstract: Indoor building construction sites are demanding environments for visual SLAM, where variable lighting and repetitive, low-textured structures make the
arXiv:2609.39346v1 Announce Type: new Abstract: Large language models (LLMs) offer strong reasoning capabilities but are often costly to access through commercial APIs, while small language models (SL
arXiv:2609.34284v2 Announce Type: replace Abstract: Personalized LLMs must decide, for each stored preference, whether the current context calls for applying or suppressing it, which we call its appli
arXiv:2604.02543v2 Announce Type: replace Abstract: As vision-language models (VLMs) are increasingly deployed in clinical decision support, more than accuracy is required: knowing when to trust their
arXiv:2609.39880v1 Announce Type: cross Abstract: Passwords remain the dominant online authentication mechanism, and understanding how humans choose them is essential for defensive strength estimation
arXiv:2609.38788v1 Announce Type: new Abstract: Organizations started listening to employees through conversational AI agents alongside structured surveys. Little is known about what these channels ch
arXiv:2512.00763v2 Announce Type: replace-cross Abstract: Adaptive and non-Euclidean optimizers often outperform Euclidean methods such as stochastic gradient descent (SGD) in language modeling by a l
arXiv:2609.39960v1 Announce Type: new Abstract: 4D scene reconstruction aims to recover the evolving geometry, appearance, and motion of dynamic environments from visual observations. Despite substant
arXiv:2609.35470v1 Announce Type: cross Abstract: Applied researchers increasingly convert images into features with pretrained encoders, then use those features in a downstream prediction model. The
arXiv:2609.40158v1 Announce Type: new Abstract: We focus on legible robot motion generation in social navigation settings. Legibility in human-robot interaction (HRI) is often described as the propert
arXiv:2609.38956v1 Announce Type: new Abstract: Routing signals of modern vision transformers -- expert gates, attention-residual weights and halting scores -- often improve probes that predict whethe
arXiv:2609.35561v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) seeks to enable AI systems to participate in improving their own capabilities. A concrete pathway is autonomous mod
arXiv:2609.38899v1 Announce Type: cross Abstract: Video Multimodal Large Language Models (Video-MLLMs) support reasoning over video inputs, yet remain vulnerable to jailbreak attacks that elicit polic
arXiv:2609.39140v1 Announce Type: new Abstract: Learning to complete tasks in unfamiliar environments with unknown rules remains a key challenge for LLM agents. Current LLM agents often record their d
arXiv:2609.39679v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) must remain effective when new spoofing attacks emerge after deployment. Emerging audio language model (ALM)-based ADD
arXiv:2609.35596v2 Announce Type: replace-cross Abstract: Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their cont
arXiv:2609.39827v1 Announce Type: cross Abstract: Pre-pretraining (PPT) on synthetic non-natural language data improves token efficiency during language model pre-training (PT). Prior work attributes
arXiv:2602.06700v2 Announce Type: replace-cross Abstract: Graph-structured data underpin a wide spectrum of modern applications, yet their multiple sensitive attributes are not isolated but deeply cou
arXiv:2609.38469v1 Announce Type: cross Abstract: Agent benchmarks test agents in worlds that stay still. Deployed agents work in worlds that other people also change. Someone texts the agent to send
arXiv:2609.39661v1 Announce Type: new Abstract: Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value ca
arXiv:2609.39235v1 Announce Type: cross Abstract: World models offer a promising way to help robots understand how the physical world evolves and plan complex behaviours through imagination. Yet exist
arXiv:2609.39114v1 Announce Type: new Abstract: This paper examines how row-wise renormalization affects Muon, focusing on the gap between NorMuon's worst-case guarantees and its practical performance
arXiv:2609.39792v1 Announce Type: new Abstract: Distinguishing periodic from chaotic dynamics in a time series is a fundamental challenge in both physics and engineering. Yet, end-to-end learned archi
arXiv:2609.39195v1 Announce Type: new Abstract: Spatial intelligence requires maintaining a coherent understanding of the world as the embodied agent moves. Like humans, the agent must use its own mot
arXiv:2609.38270v1 Announce Type: cross Abstract: Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems (LLM-ARS) instantiate users and items as autonomous agents