Knowledge catalogue
arXiv:2609.21793v1 Announce Type: cross Abstract: Defenses against jailbreak attacks on Large Language Models (LLMs) operate at different pipeline stages, such as input modification or output guard, b
arXiv:2506.07327v4 Announce Type: replace Abstract: Saliency methods are widely used to visualize which input features are deemed relevant to a model's prediction. However, their visual plausibility c
arXiv:2609.21022v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by combining semantic knowledge from pretrained vision-lang
arXiv:2609.21887v1 Announce Type: new Abstract: The gold standard datasets for mapping connectomes are electron microscopy volumes of densely labeled neural tissue at nanometer resolution. Yet reconst
arXiv:2609.21344v1 Announce Type: cross Abstract: For Internet of Things (IoT) devices, a secure algorithm alone is not enough: an attacker with physical access can attack the implementation directly,
arXiv:2609.21637v1 Announce Type: cross Abstract: Debate adjudication requires tracking how arguments develop through interaction, yet existing datasets rarely combine fine-grained debate transcripts
arXiv:2609.21872v1 Announce Type: new Abstract: We introduce Chronosphere, a spatio-temporal neural field that learns representations of climate. A central challenge in geographic representation learn
arXiv:2609.21722v1 Announce Type: cross Abstract: Chinese social media has generated a vast and continually evolving lexicon of internet buzzwords whose meanings are often non-literal and deeply roote
arXiv:2609.21686v1 Announce Type: cross Abstract: Privacy leakage in LLM agents is commonly evaluated within individual components such as memory, retrieval, or tool-use pipelines, which makes it diff
arXiv:2609.21570v1 Announce Type: cross Abstract: Renewable energy communities (RECs) coordinate buildings, photovoltaic generation, batteries, electric vehicles and flexible loads. Controller studies
arXiv:2609.21812v1 Announce Type: cross Abstract: Recent advances in diffusion models have enabled high-performance, instance-adaptive compressed sensing through posterior sampling, without task-speci
arXiv:2609.21149v1 Announce Type: new Abstract: Before patients can use AI-assisted psychiatric intake systems, health systems need practical ways to routinely evaluate these tools against their clini
arXiv:2609.21334v1 Announce Type: cross Abstract: Effective evaluation of zero-day jamming detectors requires robust adversarial models. However, existing attack models often assume prior knowledge of
arXiv:2603.12488v2 Announce Type: replace Abstract: In many robotic manipulation tasks, the robot repeatedly solves motion-planning problems that differ mainly in the location of the goal object and i
arXiv:2609.20842v1 Announce Type: new Abstract: Text-to-SQL translates natural-language questions into executable SQL queries, but open-source large language models still require task-specific post-tr
arXiv:2609.22068v1 Announce Type: new Abstract: Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-source codebases offer a rich source
coding agents are moving fast from prototype to production. the infrastructure question is what's left. join @parthsareen from @ollama and @zainhas Hasan from Together AI at @AIconference for a breako
arXiv:2609.21259v1 Announce Type: new Abstract: Understanding and modeling human intelligence are parallel goals shared by artificial intelligence (AI) and cognitive science. As AI systems grow increa
arXiv:2609.21154v1 Announce Type: new Abstract: Good tutoring adapts to the individual: it tracks what a learner knows, notices why they go wrong, and asks the next question that will help most. Most
arXiv:2508.03030v3 Announce Type: replace Abstract: Mixed-integer linear programming (MILP) has been a fundamental problem in combinatorial optimization. Conventional MILP solving mainly relies on car
arXiv:2609.21304v1 Announce Type: new Abstract: Reliable plant-level information from unmanned aerial vehicle (UAV) imagery is important for automated crop monitoring. However, in dense crop canopies,
arXiv:2609.21908v1 Announce Type: new Abstract: Although vision-language-action (VLA) policies have advanced rapidly, long-horizon execution may still progress to the next task stage before the requir
arXiv:2609.21787v1 Announce Type: new Abstract: Learned world models may have compact interventions even when their recurrent state is high-dimensional, but it is unclear what happens to such a correc
arXiv:2609.21455v1 Announce Type: new Abstract: While diffusion-based text-to-video (T2V) models have demonstrated impressive capability in generating realistic and temporally coherent videos, they of
arXiv:2609.21759v1 Announce Type: cross Abstract: We present the first complete machine learning method for accelerating plane-wave density functional theory (DFT) in materials under the projector aug
arXiv:2609.22012v1 Announce Type: new Abstract: Every multiparameter persistence vectorization we know of carries a one-sided Lipschitz upper bound and nothing below it: without a lower gauge there is
arXiv:2609.20973v1 Announce Type: cross Abstract: Complex problem solving (CPS) with large language models (LLMs) is often framed as a matter of stronger reasoning or longer generation. Yet early-step
arXiv:2609.21651v1 Announce Type: cross Abstract: Farmer.Chat is Digital Green's farm advisory service for smallholder farmers. When something looks wrong with a crop, the farmer takes a photograph an
arXiv:2609.21340v1 Announce Type: cross Abstract: Empirical identity leakage from released text is increasingly driven by attackers that combine large language models (LLMs) with auxiliary knowledge t
arXiv:2609.21387v1 Announce Type: cross Abstract: Relexicalization is a pivotal technique in clinical NLP, as it facilitates robust masking of sensitive information while synthesizing datasets that re
arXiv:2605.06445v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production
arXiv:2609.21046v1 Announce Type: new Abstract: Choreographed aquatic performances require small autonomous surface vehicles to track precise paths under per-thruster force and rate limits, including
arXiv:2609.21803v1 Announce Type: new Abstract: Contact-rich motion planning (CRMP) is essential for robotic manipulation and locomotion, yet remains computationally challenging due to combinatorial c
arXiv:2609.20906v1 Announce Type: new Abstract: Quasars are luminous objects in the universe that exhibit stochastic brightness variations encoding information about the supermassive black holes power
arXiv:2404.01897v3 Announce Type: replace-cross Abstract: Continuous graph neural networks (CGNNs) have garnered significant attention due to their ability to generalize existing discrete graph neural
Laya is an open-weight (Apache 2.0) 'System 1' decision model from Convai Innovations, built by Nandakishor M as an open alternative to TypeSafe's closed Jev API. Instead of generating text, it takes
arXiv:2601.21583v2 Announce Type: replace Abstract: Many learning problems require predicting sets of objects when the number of objects is not known beforehand. Examples include object detection, mol
arXiv:2609.21617v1 Announce Type: new Abstract: Self-play in high-throughput simulators yields driving policies with robust closed-loop performance, but improvement per unit of simulation diminishes a
arXiv:2609.21761v1 Announce Type: new Abstract: We present CRISP (Contact-RIch Simulation Platform), a high-fidelity physics engine tailored for complex multi-contact simulations such as tight-toleran
arXiv:2609.20875v1 Announce Type: cross Abstract: Parkinson's disease (PD) often manifests through speech impairments, facilitating accessible, non-invasive, and cost-effective severity assessment for
arXiv:2609.22081v1 Announce Type: new Abstract: Occupational accident narratives contain valuable information about work situations, unfavourable conditions, accident events, and their consequences. A
arXiv:2609.21347v1 Announce Type: new Abstract: Recent progress in 3D Gaussian Splatting (3DGS) has enabled dense visual SLAM with pinhole cameras, yet most pipelines are not designed for panoramic im
arXiv:2503.16094v2 Announce Type: replace Abstract: Large Language Model (LLM) alignment is commonly achieved through supervised fine-tuning or reinforcement learning, both of which require labeled or
arXiv:2609.20839v1 Announce Type: new Abstract: Phoneme-centric visual speech recognition reconstructs sentences from intermediate phoneme predictions, making overall recognition performance highly de
arXiv:2609.21427v1 Announce Type: new Abstract: Mean-variance portfolio optimization (MVO) is a central framework in data-driven asset management. A widely adopted approach is a two-stage framework th
arXiv:2609.21113v1 Announce Type: new Abstract: Fine-tuning has emerged as a widely adopted approach for adapting LLMs to a variety of downstream tasks. However, how it reshapes their internal mechani
arXiv:2511.02845v3 Announce Type: replace-cross Abstract: The advancement of next-generation Wi-Fi technology heavily relies on sensing capabilities, which play a pivotal role in enabling sophisticate
arXiv:2609.21327v1 Announce Type: cross Abstract: Quantile-based reinforcement learning provides an interpretable approach to risk-sensitive decision-making by optimizing a prescribed quantile of the
Quote: DeepSeek is training a 2T-parameter model and plans to eventually build an 8T-parameter model. https://x.com/wallstengine/status/2101982843656388644 Current DeepSeek models: Flash parameter cou
arXiv:2609.21112v1 Announce Type: new Abstract: Training a visuomotor policy calls for abundant demonstrations that closely match the target environment, yet collecting them anew remains expensive. Ex
arXiv:2609.21423v1 Announce Type: new Abstract: Online agent deployments produce abundant execution traces, while task-specific verification and expert annotation are costly to scale. We study how to
arXiv:2609.21082v1 Announce Type: new Abstract: Quadcopters offer great utility in many applications, but their nonlinear nature and disturbance sensitivity present great control challenges. Basic PID
arXiv:2609.22086v1 Announce Type: new Abstract: Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet outcomes
arXiv:2609.21096v1 Announce Type: new Abstract: In this work, we examine the topology of information flow patterns within attention graphs to effectively distinguish hallucinated from non-hallucinated
arXiv:2609.21888v1 Announce Type: cross Abstract: Detecting pretraining data in large language models is challenging because high likelihood can reflect either training exposure or strong generalizati
arXiv:2609.21628v1 Announce Type: new Abstract: Automatic tooth segmentation and FDI numbering on panoramic radiographs underpins computer-assisted dental diagnosis, yet which factors govern performan
Having a blast with Qwen Image 2.1 on my M2 Macbook Pro with 32GB RAM, even though it takes 16 minutes to complete the recommended number of iterations with the resolution reduced to 1024x1024. And th
arXiv:2609.21045v1 Announce Type: new Abstract: Collecting real-world robot data for dexterous manipulation is costly and time-consuming. While high-fidelity physics simulators enable scalable data sy
arXiv:2609.21320v1 Announce Type: cross Abstract: Modern text and image representations are often matrix-valued, with rows corresponding to tokens, patches, or other local feature vectors. Predictive
arXiv:2609.22008v1 Announce Type: cross Abstract: Vision-language models (VLMs) rely on storing and transferring appropriate information across their sub-components. Verifying that the VLMs exhibit de