Knowledge catalogue
arXiv:2605.00778v1 Announce Type: new Abstract: In biomechanical systems, observable performance is often used as a proxy for underlying system organization. However, this assumption implicitly presum
arXiv:2605.00347v1 Announce Type: cross Abstract: Given the rapidly growing capabilities of vision-language models (VLMs), extending them to interactive decision-making tasks such as video games has e
arXiv:2603.25860v2 Announce Type: replace-cross Abstract: Transformer architectures have achieved remarkable empirical success in modeling contextual relations, yet a clear understanding of their expr
arXiv:2509.12057v3 Announce Type: replace Abstract: The study of optimal decision trees has gained increasing attention in recent years; however, despite substantial progress, it still suffers from tw
This post likely describes a machine learning project implementing QLoRA (Quantized Low-Rank Adaptation) fine-tuning on the Qwen2.5-1.5B model to classify English language proficiency levels according
arXiv:2605.00707v1 Announce Type: new Abstract: Image editing instructions are heterogeneous: a color swap, an object insertion, and a physical-action edit all demand different spatial coverage and di
arXiv:2605.00517v1 Announce Type: new Abstract: Despite substantial progress in text-driven 3D human motion synthesis, generating realistic multi-person interaction sequences remains challenging. Nota
arXiv:2605.00600v1 Announce Type: cross Abstract: Deep neural networks achieve impressive results across diverse applications, yet their overconfidence on unseen inputs necessitates reliable epistemic
arXiv:2605.00825v1 Announce Type: new Abstract: Flow matching (FM) trains a time-dependent vector field that transports samples from a simple prior to a complex data distribution. However, for high-di
arXiv:2506.00158v2 Announce Type: replace Abstract: Zeroth-order optimization has emerged as a promising approach for fine-tuning large language models under differential privacy (DP) and memory const
arXiv:2605.00744v1 Announce Type: new Abstract: Edge detection refers to identifying points in a digital image where intensity changes sharply, indicating object boundaries or structural features. Cor
arXiv:2605.00747v1 Announce Type: cross Abstract: Quantum machine learning is a promising field for efficiently learning features of a dataset to perform a specified task, such as classification. Inte
arXiv:2605.00740v1 Announce Type: cross Abstract: Randomized-subspace methods reduce the cost of first-order optimization by using only low-dimensional projected-gradient information, a feature that i
arXiv:2602.18196v3 Announce Type: replace Abstract: Structured dilated attention has an appealing inference-time efficiency knob: it reduces the FLOPs of attention and the KV cache size by a factor of
arXiv:2605.00271v1 Announce Type: new Abstract: Event cameras provide several unique advantages over standard frame-based sensors, including high temporal resolution, low latency, and robustness to ex
arXiv:2501.00885v2 Announce Type: replace Abstract: The extraordinary success of recent Large Language Models (LLMs) on a diverse array of tasks has led to an explosion of scientific and philosophical
arXiv:2605.00419v1 Announce Type: cross Abstract: Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the
arXiv:2605.00489v1 Announce Type: new Abstract: We study a graph bandit setting where the objective of the learner is to detect the most influential node of a graph by requesting as little information
arXiv:2601.07349v3 Announce Type: replace Abstract: Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GR
arXiv:2602.07744v3 Announce Type: replace Abstract: Diffusion and flow models have become the dominant paradigm for generative modeling on Riemannian manifolds, with successful applications in protein
arXiv:2605.00032v1 Announce Type: cross Abstract: This work presents ROSA, a microring-based optical neural network architecture that improves robustness and energy efficiency using an optical shift-a
arXiv:2605.00510v1 Announce Type: cross Abstract: Complex physical systems, from supersonic turbulence to the macroscopic structure of the universe, are governed by continuous multiscale dynamics. Whi
arXiv:2601.21214v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning has become the standard paradigm for enabling Large Language Models (LLMs) to solve complex problems. However, rece
arXiv:2510.04378v2 Announce Type: replace Abstract: Identifying the structure of a partially observed causal system is essential to various scientific fields. Recent advances have focused on constrain
arXiv:2602.03141v3 Announce Type: replace Abstract: While Large Reasoning Models (LRMs) have demonstrated impressive capabilities in solving complex tasks through the generation of long reasoning chai
arXiv:2510.07922v4 Announce Type: replace Abstract: Decentralized Federated Learning (DFL) enables privacy-preserving collaborative training without centralized servers but remains vulnerable to Byzan
arXiv:2605.00056v1 Announce Type: new Abstract: Groundwater in the Densu Basin is increasingly threatened by heavy metal contamination, but conventional methods fail to capture the statistical complex
arXiv:2603.15988v2 Announce Type: replace-cross Abstract: Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies. However, subjective evalua
arXiv:2505.18875v4 Announce Type: replace Abstract: Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. B
arXiv:2605.00662v1 Announce Type: cross Abstract: Sequence learning reduces to similarity-based retrieval over a temporally indexed representation space, a constraint on any sequence model, not a prop
arXiv:2605.00126v1 Announce Type: new Abstract: Generative models for time-series imputation achieve strong reconstruction accuracy, yet provide no finite-sample reliability guarantees, a critical lim
arXiv:2603.18413v3 Announce Type: replace-cross Abstract: A data analysis pipeline is a structured sequence of steps that transforms raw data into meaningful insights by integrating multiple analysis
arXiv:2603.28980v2 Announce Type: replace Abstract: The synthesis of immersive 3D scenes from text is rapidly maturing, driven by novel video generative models and feed-forward 3D reconstruction, with
arXiv:2512.01116v3 Announce Type: replace Abstract: The integration of histology images and gene profiles has shown great promise for improving survival prediction in cancer. However, current approach
arXiv:2507.09001v3 Announce Type: replace-cross Abstract: Machine learning (ML) models for electronic structure typically rely on large datasets generated by computationally expensive Kohn-Sham densit
The AI market is full of big promises of grand transformation. Health care is a prime target for those promises, beset as it is by financial pressures, labor shortages, and the growing burden of carin
arXiv:2605.00140v1 Announce Type: cross Abstract: We present Activation Residual Hessian Quantization (ARHQ), a post-training weight splitting method designed to mitigate error propagation in low-bit
arXiv:2605.00738v1 Announce Type: new Abstract: With the proliferation of Electronic Health Records (EHRs), a critical challenge in building predictive models is determining the optimal historical dat
arXiv:2601.09896v4 Announce Type: replace-cross Abstract: Visual generative AI models are trained using a one-size-fits-all measure of aesthetic appeal. However, what is deemed 'aesthetic' is inextric
The article discusses concerns about the widespread use of knowledge distillation in AI development, where larger models' outputs are used to train smaller models, potentially creating a cycle of degr
arXiv:2512.19927v2 Announce Type: replace Abstract: Seismology faces fundamental challenges in state forecasting and reconstruction (e.g., earthquake early warning and ground motion prediction) and ma
arXiv:2603.17837v3 Announce Type: replace-cross Abstract: During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal c
arXiv:2506.11989v3 Announce Type: replace Abstract: Test-time scaling offers a promising way to improve the reasoning performance of vision-language large models (VLLMs) without additional training. I
arXiv:2605.00143v1 Announce Type: new Abstract: Humor is a fundamental cognitive phenomenon in which humans derive pleasure from the expectation violations and their resolution, exemplifying the brain
arXiv:2602.03216v2 Announce Type: replace Abstract: The quadratic complexity of attention remains the central bottleneck in long-context inference for large language models. Prior acceleration methods
arXiv:2605.00488v1 Announce Type: new Abstract: In multi-armed bandits, the most-explored arms are the most informative, while reward maximization typically pulls only the best arm. We study the trade
arXiv:2605.00414v1 Announce Type: new Abstract: Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work u
arXiv:2605.00297v1 Announce Type: cross Abstract: Traditionally, machine learning methods for PE malware detection have relied on static features like byte histograms, string information, and PE heade
arXiv:2605.00052v1 Announce Type: new Abstract: Hybrid-capture novel view synthesis combines images at substantially different camera distances (e.g., aerial drone and ground-level views). Standard 3D
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:2605.00638v1 Announce Type: new Abstract: Machine unlearning aims to unlearn data points from a learned model, offering a principled way to process data-deletion requests and mitigate privacy ri
VANISHING CULTURE is out now! From Internet Archive, this book looks at what is disappearing online. 🌐 Websites vanish 🗞️ News archives go offline 🎮 Games become unplayable 📼 Personal media breaks & b
arXiv:2603.22285v2 Announce Type: replace Abstract: Long video understanding remains challenging for multimodal large language models (MLLMs) due to limited context windows, which necessitate identify
arXiv:2605.00354v1 Announce Type: new Abstract: Many diffusion based molecule generation methods ignore the symbolic information of molecules and represent the atom and bond type as one hot representa
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Two of the most powerful people in AI—Sam Altman and Elon Musk
arXiv:2605.00497v1 Announce Type: cross Abstract: Recent advances in user modeling make it feasible to conduct open-ended inference over a person's everyday computer use. Despite longstanding visions
arXiv:2511.16767v2 Announce Type: replace Abstract: Graphs provide a unified representation of semantic content and relational structure, making them a natural fit for domains such as molecular modeli
arXiv:2602.13305v2 Announce Type: replace Abstract: Wildfires are a growing threat to ecosystems, human lives, and infrastructure, with their frequency and intensity rising due to climate change and h
Sebastian Raschka maintains a comprehensive gallery of LLM architecture diagrams and visualizations on his website, with higher-resolution versions available at sebastianraschka.com/llm-architecture-g
This post documents a second wave of large language model and AI architecture releases from April, featuring updates from multiple organizations including Ant Ling 2.6 1T, Minimax M2.7, Xiaomi MiMo V2