Knowledge catalogue
arXiv:2609.01016v1 Announce Type: new Abstract: Current speech synthesis struggles with code-switching, which mixes a foreign language phrase into a primary language utterance, causing the phrase to b
Quite surprised to be beating other high quality quants. It took a lot of benchmarking to get here and we are quite pleased with these, hope they are useful to the community. It required a modified wa
arXiv:2609.00628v1 Announce Type: cross Abstract: Global welfare often depends on the correct interpretation of aerial and satellite imagery. Acting on such imagery (mapping flooded ground, crop exten
arXiv:2609.00385v1 Announce Type: cross Abstract: Autonomous highway overtaking demands foresighted decision-making to handle complex interactions, stochastic traffic evolution, and temporal risk accu
arXiv:2609.01224v1 Announce Type: new Abstract: Visual token pruning reduces the inference overhead of multimodal large language models (MLLMs) by retaining only a subset of visual tokens. Existing me
arXiv:2607.17122v2 Announce Type: replace Abstract: Scope 3 greenhouse gas (GHG) emissions account for the majority of corporate carbon footprints, yet remain difficult to analyze at scale due to spar
arXiv:2609.01035v1 Announce Type: new Abstract: Recursive LLM agents can broaden their search by spawning specialists. Some branches later request tools that send data or deploy code. When should a br
arXiv:2609.00264v1 Announce Type: new Abstract: Chain-of-thought monitoring is proposed for AI oversight, yet evaluations often provide monitors with a trusted reference answer. We ask whether answer
The winning interface for generative media will not be a prompt box. Regulators want the chain traceable. The EU's marking rules took effect Aug 2, and the mark has to survive to the delivered file. B
Today we’re open-sourcing Lily, the local inference engine we built for hybrid compute in Perplexity Computer. Lily is specialized for Qwen3.6-35B-A3B on Apple silicon, built so on-device compute does
arXiv:2609.00597v1 Announce Type: new Abstract: With the rapid rise of large language models (LLMs), controlling undesirable model behaviors has become increasingly important. Existing behavioral cont
arXiv:2609.01202v1 Announce Type: cross Abstract: Clinical trials are essential for advancing cancer care and drug development, but many fail because of insufficient patient enrollment. While there is
arXiv:2609.00507v1 Announce Type: new Abstract: Accurate prediction of unsteady separated flows is challenging because the aerodynamic loads depend on nonlinear separation and vortex-shedding dynamics
arXiv:2609.01420v1 Announce Type: new Abstract: Cooperation in multi-UAV systems requires reliable relative perception so that follower vehicles can maintain formation and continue their mission safel
arXiv:2609.00830v1 Announce Type: cross Abstract: Whether attention weights faithfully reflect model reasoning has been actively debated in NLP, yet this question remains largely unexplored for the vi
arXiv:2608.28652v1 Announce Type: new Abstract: Artificial intelligence (AI) models have demonstrated remarkable capabilities across various domains, yet their widespread deployment is impeded by sign
arXiv:2608.30088v1 Announce Type: new Abstract: Accurate detection of tomato growth stages is essential for stage-specific greenhouse management and precision agriculture. In Bhutan, greenhouse cultiv
arXiv:2608.30105v1 Announce Type: cross Abstract: Deep learning-based side-channel analysis has historically focused on single-byte targets and manually cropped traces, which risks discarding exploita
Just to name a few: running Qwen3 8B on a 32GB GPU running Qwen3.6-27B Q4_K_M on 2 x R9700 quote: 'each prompt was sized at 500 input and 500 output tokens' for a full system that costs $18,775?? I do
arXiv:2608.29831v1 Announce Type: new Abstract: Localizing issue-relevant code regions is a critical step in automated software engineering. However, due to their reliance on sparse trajectory-level s
arXiv:2608.28676v1 Announce Type: new Abstract: Digitized herbarium collections, now comprising over 100 million freely accessible specimen images, have become a critical resource for addressing funda
arXiv:2608.29232v1 Announce Type: cross Abstract: Object detectors are typically trained under closed-set supervision, where unlabeled regions are implicitly treated as background. Under incomplete an
arXiv:2608.30467v1 Announce Type: new Abstract: Deep-learning models can achieve strong chest X-ray (CXR) classification performance without establishing whether their predictions predominantly rely o
arXiv:2608.30897v1 Announce Type: new Abstract: World models are becoming core infrastructure for embodied intelligence, with action-conditioned video generation providing controllable predictions of
arXiv:2608.30242v1 Announce Type: new Abstract: While visual navigation has advanced through imitation learning from cross-platform demonstrations, fully leveraging such data remains challenging. Firs
arXiv:2604.01113v2 Announce Type: replace Abstract: Large language model (LLM) systems are increasingly used to support high-stakes decision-making, but they typically perform worse when the available
arXiv:2608.30758v1 Announce Type: new Abstract: Recent radiology multi-modal language models have made substantial progress in chest X-ray report generation, visual question answering, and temporal re
arXiv:2608.29621v1 Announce Type: cross Abstract: Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt cons
arXiv:2608.28677v1 Announce Type: new Abstract: This paper presents l{CogRun}, a framework that enables safety-critical ground robots to perform cognitively-grounded runtime learning entirely on edge-
arXiv:2608.30974v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architecture (JEPA) has shown strong performance in learning rich representations through self-supervised prediction in lat
arXiv:2608.30674v1 Announce Type: cross Abstract: Accurate molecular property prediction requires both statistical reliability and chemical reasoning. Graph neural networks can be calibrated directly
arXiv:2608.29223v1 Announce Type: new Abstract: Accurate through-thickness measurement of subsurface delamination depth in Carbon Fiber Reinforced Polymer (CFRP) is important for structural assessment
arXiv:2603.26509v2 Announce Type: replace Abstract: Computed tomography (CT) provides rich 3D anatomical detail but is often constrained by high radiation exposure, substantial costs, and limited avai
arXiv:2608.29675v1 Announce Type: cross Abstract: Repository exploration is a distinct and costly stage of coding-agent pipelines: before generating a patch, an agent must identify which repository fi
arXiv:2608.29674v1 Announce Type: new Abstract: Sharing tabular data in high-stakes domains is constrained by privacy regulations. Synthetic data offer a promising alternative, but deep generative mod
arXiv:2607.11577v2 Announce Type: replace-cross Abstract: Conventional Graph Neural Networks (GNNs) couple feature transformation and neighborhood aggregation, which often renders them vulnerable to t
arXiv:2608.30543v1 Announce Type: new Abstract: Large Language Models (LLMs) offer new possibilities for scaling qualitative analysis, but existing applications often provide limited methodological tr
arXiv:2608.28970v1 Announce Type: cross Abstract: Current TTS systems typically rely on open-loop, single-pass generation and can produce sporadic local prosodic defects, such as misplaced stress, unn
arXiv:2608.29264v1 Announce Type: new Abstract: Diffusion-based visual generative models deliver strong image and video synthesis quality but incur high inference costs because sequential samplers rep
arXiv:2608.29027v1 Announce Type: new Abstract: Shrimp disease classification has become an urgent issue due to its significant impact on the import-export output of producing countries, particularly
arXiv:2608.28777v1 Announce Type: new Abstract: Although recent deepfake detectors achieve high overall accuracy, their errors remain unevenly distributed across demographic subgroups, with real faces
arXiv:2608.28672v1 Announce Type: new Abstract: Autonomous vehicles operate in dynamic, ever-changing environments where new scenarios and edge cases constantly emerge. As a result, static learning mo
arXiv:2510.23515v3 Announce Type: replace Abstract: This paper proposes FreeFuse, a training-free framework for multi-subject text-to-image generation through automatic fusion of multiple subject LoRA
arXiv:2608.28619v1 Announce Type: cross Abstract: Medical history taking is a dialogue-based clinical reasoning task in which learners must gather, organise, and integrate patient information while th
arXiv:2608.30550v1 Announce Type: new Abstract: Multimodal Sewing pattern generation aims to infer executable sewing patterns from design cues such as sketches and textual descriptions. As an interpre
arXiv:2608.29211v1 Announce Type: new Abstract: Ground image localization with respect to satellite imagery is a key enabler for metrically-accurate, geo-localized 3D scene reconstruction from unconst
arXiv:2608.29313v1 Announce Type: cross Abstract: CLIP-like vision-language models (VLMs) trained with contrastive objectives learn strong global image-text representations, but their Euclidean embedd
Yoyo I'm back with updates to the fastest inference engine with minimal quality loss for Qwen3.8-27B. The last few weeks I've been optimizing decode speed and I don't think it can be pushed further, u
arXiv:2608.29349v1 Announce Type: new Abstract: Gaussian process (GP) regression with a single global GP (GP-glo) incurs cubic computational cost, limiting scalability to large datasets. Product-of-ex
arXiv:2608.30034v1 Announce Type: new Abstract: Two-stage vision pipelines often place an enhancement network before a task network, on the assumption that a cleaner input produces a better output. We
arXiv:2508.08966v2 Announce Type: replace Abstract: The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a grow
arXiv:2608.29901v1 Announce Type: cross Abstract: Electronic Health Record (EHR) prediction models in the intensive care unit must learn from sparse and irregular measurements while preserving the cli
arXiv:2512.17452v4 Announce Type: replace-cross Abstract: Long-context LLM inference is bottlenecked by the quadratic attention complexity and linear Key-Value (KV) cache growth. Prior approaches miti
arXiv:2607.10851v2 Announce Type: replace Abstract: Medical image classification models are ideally expected to identify diagnostically relevant regions while making predictions, yet standard classifi
arXiv:2608.29268v1 Announce Type: new Abstract: PCB engineering drawings mix sparse graphics, dense tables, and text whose meaning depends on page position. Localizing the regions and sending crops to
arXiv:2608.30773v1 Announce Type: new Abstract: In animals such as elephants and octopuses, acquiring non-visual information about an object and physically engaging with it are inseparable processes m
arXiv:2608.29612v1 Announce Type: new Abstract: Sustained scientific work requires a knowledge substrate that carries interpretation across tasks and preserves paths to source evidence. We call this p
arXiv:2502.10577v2 Announce Type: replace-cross Abstract: Instruct-based large language models (LLMs) have been shown to propagate and even amplify gender bias when prompted with contextually constrai
arXiv:2608.28724v1 Announce Type: new Abstract: Planetary surface exploration missions rely increasingly on autonomous robotic platforms capable of interpreting complex terrain to ensure safe navigati
arXiv:2608.28670v1 Announce Type: new Abstract: Diffusion Transformers achieve high-fidelity image and video generation, but their iterative sampling remains expensive, for each denoising step require