Efficient Pre-Training with Token Superposition
arXiv:2605.06546v2 Announce Type: replace Abstract: Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in ord
Knowledge catalogue
arXiv:2605.06546v2 Announce Type: replace Abstract: Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in ord
arXiv:2605.19394v1 Announce Type: cross Abstract: Adapting small instruction-tuned models to specialized domains often relies on supervised fine-tuning (SFT) on curated instruction-response examples,
arXiv:2605.19630v1 Announce Type: new Abstract: With every advancement in generative AI models, forensics is under increasing pressure. The constant emergence of new generation techniques makes it imp
arXiv:2604.02784v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) excel at multimodal tasks, but they remain vulnerable to hallucinations that are factually incorrect or unground
arXiv:2605.19556v1 Announce Type: new Abstract: Estimating relative pose from image pairs fundamentally requires only a minimal subset of geometrically consistent correspondences. However, most learni
arXiv:2605.19243v1 Announce Type: cross Abstract: We study the problem of recovering a globally consistent Euclidean embedding of data, given only a local distance graph and propose a method that opti
arXiv:2605.19258v1 Announce Type: cross Abstract: Deep learning has enabled ECG diagnostic models with strong performance in tasks such as arrhythmia classification and abnormality detection. However,
arXiv:2605.19859v1 Announce Type: new Abstract: Vision-language models (VLMs) have rapidly evolved into general-purpose multimodal reasoners with strong zero-shot generalization. In this context, VLMs
arXiv:2605.19291v1 Announce Type: cross Abstract: Stochastic gradient descent (SGD) is a fundamental optimization algorithm widely used in modern machine learning. In this paper, we propose Factor-Aug
arXiv:2605.19786v1 Announce Type: new Abstract: 4D mesh generation has recently emerged as a powerful paradigm for recovering dynamic 3D structure from videos, but existing methods remain slow, comput
arXiv:2605.19842v1 Announce Type: new Abstract: We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomp
arXiv:2605.18789v1 Announce Type: cross Abstract: Features in language models have life history: they emerge, persist, and die during training, yet the importance of that history remains largely unexp
arXiv:2601.01901v2 Announce Type: replace Abstract: Data-free knowledge distillation-based one-shot federated learning (OSFL) trains a model in a single communication round without sharing raw data, m
arXiv:2310.11203v2 Announce Type: replace Abstract: We introduce a novel strategy to train randomised predictors in federated learning, where each node of the network aims at preserving its privacy by
arXiv:2605.20016v1 Announce Type: cross Abstract: Short-form video poses new challenges to the quality assessment of user-generated content (UGC) due to its complex generation pipeline, rapid content
arXiv:2605.19224v1 Announce Type: new Abstract: Neuroscientists have recently turned to intracranial brain recording methods, like electrocorticography (ECoG), for human experiments because of the fin
arXiv:2605.20005v1 Announce Type: new Abstract: Fine-tuning large language models on new data improves task performance but degrades capabilities learned during pretraining, a phenomenon known as cata
arXiv:2509.25448v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it ch
arXiv:2605.19150v1 Announce Type: cross Abstract: State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's tra
arXiv:2605.20022v1 Announce Type: new Abstract: Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and
arXiv:2605.19279v1 Announce Type: new Abstract: Visual image reconstruction from functional Magnetic Resonance Imaging (fMRI) is a fundamental task in brain decoding, providing a crucial pathway for u
arXiv:2605.18923v1 Announce Type: cross Abstract: Accurate selection of bovine embryos is a challenging task, as current practice relies on a single expert assessment on the seventh day after insemina
arXiv:2503.11615v3 Announce Type: replace Abstract: Sampling from an unknown distribution, accessible only through discrete samples, is a fundamental problem at the core of generative AI. The current
arXiv:2605.20177v1 Announce Type: new Abstract: Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is prima
arXiv:2511.16062v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) excel on homophilous graphs but often fail under heterophily due to self-reinforcing and phase-inconsistent signals. We
arXiv:2605.18873v1 Announce Type: cross Abstract: Training and evaluating false data injection attack (FDIA) detectors for power systems is constrained by data scarcity. Operational grid measurements
arXiv:2605.19376v1 Announce Type: new Abstract: How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregres
arXiv:2605.19734v1 Announce Type: new Abstract: Multi-source remote sensing enables complementary observation of ground objects, while cross-modal fine-grained object retrieval remains challenging, es
arXiv:2605.19889v1 Announce Type: cross Abstract: 3D Lookup Tables (3D LUTs) are widely used for color mapping, but their grid-based representation requires discretizing the RGB space, leading to a ca
arXiv:2605.19119v1 Announce Type: cross Abstract: Existing neural combinatorial optimization solvers frame solution search as imitation of optimal decisions, inherently limiting their utility to singl
arXiv:2605.20145v1 Announce Type: cross Abstract: Bayesian optimization (BO) selects evaluation points for expensive black-box objectives using Gaussian process (GP) predictive distributions. Kernel c
arXiv:2504.05454v2 Announce Type: replace-cross Abstract: Explainability is necessary for many tasks in biomedical research. Recent explainability methods have focused on attention, gradient, and Shap
arXiv:2407.20595v4 Announce Type: replace-cross Abstract: Deciding whether two pieces of text share an author is made difficult by topical confound: two writers covering the same topic often look more
arXiv:2605.20167v1 Announce Type: new Abstract: Flash floods in Bangladesh's haor wetlands show up with almost no warning. They wreck the annual boro rice harvest. Current setups, built for riverine f
arXiv:2511.21577v2 Announce Type: replace-cross Abstract: The availability of high-quality, AI-generated audio raises security challenges such as misinformation campaigns and voice-cloning fraud. A ke
IBM researchers have achieved a record-breaking quantum circuit by advancing quantum computing benchmarking and performance capabilities. The work likely demonstrates progress in quantum algorithm imp
arXiv:2605.18932v1 Announce Type: cross Abstract: In this work, we propose HypergraphFormer, a novel and efficient approach to floor plan generation based on learning hypergraph representations with a
arXiv:2605.19135v1 Announce Type: new Abstract: Causal representation learning (CRL) seeks to uncover meaningful latent variables and their corresponding causal structure from high-dimensional observa
I'm switching to Hermes.... I've been using it for a month.....and I'm sold...moving all of my @openclaw agents to Hermes (@NousResearch) Why? -----> https://youtu.be/QQEgIo4Juxg Thank you to @Hosting
Imagine if Biden: • Created a 1.8 billion slush fund to hand out to rioters who assaulted police officers • Banned the IRS from auditing him, his family, and his companies • Accepted a 400 million lux
arXiv:2605.19317v1 Announce Type: cross Abstract: Inference-time scaling has emerged as a major approach for improving reasoning capabilities, and has been increasingly applied to diffusion models. Ho
arXiv:2605.19042v1 Announce Type: new Abstract: Machine unlearning aims to remove the contribution of designated training data from a trained model while preserving performance on the remaining data.
arXiv:2605.19982v1 Announce Type: new Abstract: Low-Light Image Enhancement (LLIE) has long been a challenging problem in low-level vision, as insufficient illumination often leads to low contrast, de
arXiv:2605.20159v1 Announce Type: new Abstract: Non-destructive testing of aerospace SiC/SiC composites via X-ray computed tomography (XCT) relies on expert visual assessment, with current workflows o
Nous Research announced a new feature called 'skill bundles,' which likely refers to packaged collections of AI capabilities or competencies that can be grouped together for more efficient deployment
arXiv:2605.19523v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable proficiency in general multi-modal understanding; yet they struggle to efficiently acquire
arXiv:2605.19840v1 Announce Type: new Abstract: For most of human history, we have not thought systematically about how and why we incorporate aspects of the natural world into our designs. The lack o
arXiv:2605.20170v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) have shown impressive performances in user-facing tasks such as question answering, as well as consistent improvemen
arXiv:2605.19049v1 Announce Type: cross Abstract: Linear attention has recently gained significant attention for long-context inference due to its constant decoding cost with respect to context length
arXiv:2507.01123v2 Announce Type: replace Abstract: Landslides pose severe threats to infrastructure, economies, and human lives, necessitating accurate detection and predictive mapping across diverse
arXiv:2605.20050v1 Announce Type: new Abstract: This study investigates how language mutations affect the persistent diffusion of conspiracy theories on social media. Drawing on a three-year dataset o
arXiv:2510.27588v3 Announce Type: replace-cross Abstract: We consider the task of constructing a data structure for associating a static set of keys with values, while allowing arbitrary output values
arXiv:2506.01529v2 Announce Type: replace Abstract: Learning meaningful abstract models of Markov Decision Processes (MDPs) is crucial for improving generalization from limited data. In this work, we
arXiv:2605.19074v1 Announce Type: cross Abstract: The rapid global expansion of solar photovoltaic (PV) capacity-reaching a record 597 GW in 2024-highlights the urgent need for robust forecasting mode
arXiv:2605.19959v1 Announce Type: new Abstract: Infinite-dimensional orthonormal basis expansions play a central role in representing and computing with function spaces due to their favorable linear a
arXiv:2602.04998v2 Announce Type: replace-cross Abstract: Low-Rank Adaptation (LoRA) is the prevailing approach for efficient large language model (LLM) fine-tuning. Building on this paradigm, recent
arXiv:2504.00470v2 Announce Type: replace-cross Abstract: To develop a trustworthy AI system, which aim to identify the input regions that most influence the models decisions. The primary task of exis
arXiv:2605.19060v1 Announce Type: cross Abstract: High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slic
arXiv:2605.19811v1 Announce Type: new Abstract: In large-scale optimization, the cheapness and effectiveness of update steps are the most crucial factors for a successful optimizer. Sign-based optimiz
arXiv:2605.19714v1 Announce Type: new Abstract: Investor sentiment shapes financial markets, yet modeling sentiment in Arabic financial contexts remains challenging due to linguistic complexity and li