Knowledge catalogue
arXiv:2603.18066v2 Announce Type: replace-cross Abstract: Backpropagation has enabled modern deep learning but is difficult to realize as an online, fully distributed hardware learning system due to g
arXiv:2605.01345v1 Announce Type: new Abstract: Visual perception in modern Vision-Language Models (VLMs) is constrained by a fundamental perceptual bandwidth bottleneck: a broad field of view inevita
arXiv:2605.01355v1 Announce Type: new Abstract: Automated leaf disease classification is critical for early disease detection in resource-constrained field environments. Vision Transformers (ViTs) pro
arXiv:2508.12535v3 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in
DeepSeek v4 works fine, but it’s not the frontier-pressing moment we saw with Kimi 2.6. On Notion eval data, it’s similar performance to GPT 5.2, with understandable failings. Most interesting — it do
arXiv:2605.01372v1 Announce Type: new Abstract: Large language models (LLMs) have been widely explored for embedding generation. While recent studies show that in-context learning (ICL) effectively en
arXiv:2605.02464v1 Announce Type: new Abstract: Single-image HDR reconstruction aims to recover high dynamic range radiance from a single low dynamic range (LDR) input, but remains highly ill-posed du
arXiv:2605.01959v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA) have become essential for deploying large language models, yet their static pa
arXiv:2605.02130v1 Announce Type: new Abstract: Human-level agentic intelligence extends beyond low-level geometric perception, evolving from recognizing where things are to understanding what they ar
arXiv:2605.02665v1 Announce Type: new Abstract: In Emotion Recognition in Conversations (ERC), model decisions should align with nuanced human perception and ideally provide insights on the classifica
arXiv:2605.01581v1 Announce Type: new Abstract: Diffusion-based visuomotor policies perform well in robotic manipulation, yet current methods still inherit image-generation-style decoders and multi-st
arXiv:2510.25426v2 Announce Type: replace Abstract: The rapid advancement of Large Language Models (LLMs) is positioning language at the core of human-computer interaction (HCI). We argue that advanci
arXiv:2605.01742v1 Announce Type: new Abstract: Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments
arXiv:2510.10245v2 Announce Type: replace-cross Abstract: Adaptive experiments improve efficiency by adjusting treatment assignments based on past outcomes, but this adaptivity breaks the i.i.d. assum
arXiv:2605.00925v1 Announce Type: cross Abstract: Integrating molecular, morphological, and clinical data is essential for basic and translational biomedical research, yet systematic frameworks for jo
arXiv:2605.02641v1 Announce Type: new Abstract: We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture.
arXiv:2603.10584v2 Announce Type: replace Abstract: We introduce Marigold-SSD, a single-step, late-fusion depth completion framework that leverages strong diffusion priors while eliminating the costly
arXiv:2506.22899v3 Announce Type: replace Abstract: Neural Cellular Automata (NCAs) are bio-inspired dynamical systems in which identical cells iteratively apply a learned local update rule to self-or
NEW paper from Microsoft Research. Nice study on long-horizon agent generalization. (bookmark it) The team runs a study where the only variable is task horizon length. They use the same decision rules
arXiv:2605.02675v1 Announce Type: cross Abstract: This paper introduces an extension of generalised filtering for online applications. Generalised filtering refers to data assimilation schemes that jo
arXiv:2605.02714v1 Announce Type: new Abstract: The advent of foundation models has heralded a new era in medical artificial intelligence (AI), enabling the extraction of generalizable representations
arXiv:2605.01552v1 Announce Type: new Abstract: In this paper, we introduce a challenging task: extracting a fundamental matrix from a single motion blurred image. For a camera moving in 3D during exp
// Skills as Verifiable Artifacts // Pay attention to this one, AI devs. If you ship agent skills, your runtime is treating signed-and-cleared skills as trusted by default. This paper argues a skill i
arXiv:2605.02860v1 Announce Type: cross Abstract: Cross-language code clone detection (X-CCD) is challenging because semantically equivalent programs written in different languages often share little
arXiv:2605.02404v1 Announce Type: new Abstract: Model quantization has become essential for efficient large language model deployment, yet existing approaches involve clear trade-offs: methods such as
arXiv:2602.08245v2 Announce Type: replace Abstract: Diffusion policies have recently emerged as a powerful paradigm for visuomotor control in robotic manipulation due to their ability to model the dis
arXiv:2504.17401v2 Announce Type: replace Abstract: Stereo disparity estimation is crucial for obtaining depth information in robot-assisted minimally invasive surgery (RAMIS). While current deep lear
arXiv:2605.02102v1 Announce Type: cross Abstract: Reliable and secure human-machine communication is fundamental to IoT and cyber-physical ecosystems, where smartphones and wearables commonly serve as
arXiv:2506.01097v2 Announce Type: replace Abstract: Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficien
arXiv:2605.02427v1 Announce Type: cross Abstract: A recurring pattern in 'reasoning without training' is that base LLMs already assign non-trivial probability mass to correct multi-step solutions; the
arXiv:2605.00737v1 Announce Type: new Abstract: Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities. However, tool use is not always beneficial; some calls may be
arXiv:2605.02735v1 Announce Type: new Abstract: Continuous latent-space reasoning offers a compact alternative to textual chain-of-thought for multimodal models, enabling high-dimensional visual evide
arXiv:2409.14204v4 Announce Type: replace-cross Abstract: Deep learning has shown significant value in medical image registration for motion correction, however, current techniques are either limited
arXiv:2507.18064v2 Announce Type: replace Abstract: Most existing low-light image enhancement (LLIE) methods rely on pre-trained model priors, low-light inputs, or both, while neglecting the semantic
arXiv:2605.00374v1 Announce Type: new Abstract: Edge classification, a crucial task for graph applications, remains relatively under-explored compared to link prediction. Current methods often overloo
arXiv:2605.00369v1 Announce Type: new Abstract: We study how large language models can be used to evolve inventory policies in online, non-stationary environments. Our work is motivated by recent adva
The search results show recent llama.cpp releases but not the specific b9015 release details. Based on the pattern found (b9010 is mentioned as the latest release from the search results), b9015 is li
B9022 is a release of llama.cpp created on May 4, 2026, with commit d8794ee signed with GitHub's verified signature. The llama.cpp project is the main playground for developing new features for the gg
arXiv:2605.00330v1 Announce Type: new Abstract: Operator learning enables fast surrogate modeling of high-dimensional dynamical systems, but existing approaches face two fundamental limitations: quadr
arXiv:2605.00082v1 Announce Type: new Abstract: The Forward-Forward (FF) algorithm presents a compelling, bio-inspired alternative to backpropagation. However, while efficient in training, it has a co
arXiv:2508.07630v2 Announce Type: replace Abstract: We introduce InterChart, a diagnostic benchmark that evaluates how well vision-language models (VLMs) reason across multiple related charts, a task
arXiv:2605.00434v1 Announce Type: new Abstract: Real-world multimodal learning is often hindered by missing modalities. While Incomplete Multimodal Learning (IML) has gained traction, existing methods
arXiv:2605.00475v1 Announce Type: cross Abstract: Real-world fine manipulation, particularly in bimanual manipulation, typically requires low-latency control and stable visual localization, while coll
arXiv:2512.16762v3 Announce Type: replace Abstract: Generative Pre-trained Transformer (GPT) architectures are the most popular design for language modeling. Energy-based modeling is a different parad
arXiv:2605.00536v1 Announce Type: cross Abstract: Scaling laws for Large Language Models (LLMs) establish that model quality improves with computational scale, yet edge deployment imposes strict const
arXiv:2511.05582v2 Announce Type: replace Abstract: Real-Time Auction (RTA) Interception aims to filter out invalid or irrelevant traffic to enhance the integrity and reliability of downstream data. H
arXiv:2509.24255v2 Announce Type: replace-cross Abstract: As virtual reality (VR) becomes widespread, head and hand motion data captured by consumer systems has become substantially more common. Howev
arXiv:2604.28109v1 Announce Type: new Abstract: Model merging has attracted attention as an effective path toward multi-task adaptation by integrating knowledge from multiple task-specific models. Amo
arXiv:2604.26986v1 Announce Type: new Abstract: We introduce a novel task of digital battery passport (DBP) conformance classification and introduce the first public benchmark for the task: BatteryPas
arXiv:2604.27004v1 Announce Type: cross Abstract: We propose EdgeSpike, a co-designed spiking neural network (SNN) framework for autonomous low-power sensing in edge Internet of Things (IoT) architect
arXiv:2604.27906v1 Announce Type: new Abstract: Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant contex
arXiv:2410.05284v2 Announce Type: replace-cross Abstract: Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentia
arXiv:2512.07808v2 Announce Type: replace-cross Abstract: Qubit readout is a critical operation in quantum computing systems, which maps the analog response of qubits into discrete classical states. D
arXiv:2604.26963v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators. Agentic w
arXiv:2604.27792v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models achieve strong semantic generalization but often lack fine-grained modeling of world dynamics. Recent work explores
arXiv:2604.27911v1 Announce Type: new Abstract: Foundation models are deep neural networks (such as GPT-5, Gemini~3, and Opus~4) trained on large datasets that can perform diverse downstream tasks --
arXiv:2604.27322v1 Announce Type: new Abstract: Recent advances in Diffusion Transformer (DiT)-based video generation technologies have shown impressive results for video object removal. However, thes
arXiv:2604.26351v1 Announce Type: new Abstract: Language models (LMs) behave more like humans when their cognitive resources are restricted, particularly in predicting sentence processing costs such a
arXiv:2603.25980v2 Announce Type: replace-cross Abstract: Transition states, the first-order saddle points on the potential energy surfaces, govern the kinetics and mechanisms of chemical reactions an
arXiv:2604.26492v1 Announce Type: cross Abstract: Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often m