Knowledge catalogue
arXiv:2605.08475v1 Announce Type: cross Abstract: Mechanistic accounts of in-context learning (ICL) have identified iterative algorithms for linear regression and related linear prediction tasks, ofte
arXiv:2502.07553v2 Announce Type: replace Abstract: Learning sparse parity functions has become a theoretical testbed for studying feature learning in neural networks. However, existing analyses prima
arXiv:2605.08633v1 Announce Type: cross Abstract: Earth observation is becoming one of the largest data-producing activities in science, yet current pipelines still treat compression as a storage and
arXiv:2605.10705v1 Announce Type: new Abstract: Transmissive scenes are ubiquitous in daily life, yet reconstructing and rendering them remains highly challenging due to the inherent entanglement betw
arXiv:2605.08278v1 Announce Type: cross Abstract: GNNs have become a standard tool for learning on relational data, yet they remain highly vulnerable to backdoor attacks. Prior defenses often depend o
Trial lawyers missed a great chance to ask everyone on the stand, under oath, what their definition of AGI is sam altman, under oath, clarifies that microsoft will lose access to openai’s research IP
arXiv:2511.03368v2 Announce Type: replace Abstract: The rise of the machine learning (ML) model economy has intertwined markets for training datasets and pre-trained models. However, most pricing appr
Trump campaigned on bringing down the cost of living 'starting on day one,' and then: started a trade war; deported much of the farm workforce, bombed Iran, allowed healthcare subsidies to expire, cut
Trump had one of his worst mental health episodes yet last night, posting over 55 times in 3 hours. Here is the list: 10:15 PM - Accuses Obama of attempting a coup in 2016 10:15 PM - Says Obama worked
arXiv:2605.08964v1 Announce Type: new Abstract: In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML sy
Try Grok Voice Grok Voice Think Fast 1.0 ranks #1 on the Artificial Analysis τ-Voice benchmark for real-world agentic customer service resolution Absolutely outperforming GPT-Realtime-2 (High) and Gem
arXiv:2605.09208v1 Announce Type: new Abstract: Although many complex models were proposed to analyze time series data, some studies have demonstrated remarkable performance with simpler structures. A
arXiv:2605.08111v1 Announce Type: cross Abstract: The widespread availability of complex time series data in various domains such as environmental science, epidemiology, and economics demands robust c
arXiv:2412.13547v3 Announce Type: replace Abstract: Novel-view synthesis plays a crucial role in computer vision with applications in 3D reconstruction, mixed reality, and robotics. Recent approaches,
arXiv:2605.09227v1 Announce Type: new Abstract: [Abridged] Using a Large Language Model (LLM) as an automatic rater (LLM-as-a-judge) is cheap but potentially biased: some judges run lenient, others st
arXiv:2605.10715v1 Announce Type: new Abstract: Landslide monitoring and simulation play an important role in urban safety assessment and disaster prevention. Existing landslide simulation pipelines t
arXiv:2605.09862v1 Announce Type: cross Abstract: Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve
arXiv:2605.08376v1 Announce Type: new Abstract: Underwater image enhancement (UIE) is a practically important yet underexplored application of spiking neural networks (SNNs), where the dominant degrad
arXiv:2601.08321v3 Announce Type: replace Abstract: With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main
arXiv:2605.08288v1 Announce Type: cross Abstract: Device-free localization trains models from heterogeneous wireless and visual sensors (e.g., Wi-Fi, LiDAR) distributed across edge devices. Federated
Uncensored LLMs are architectures that have been modified or fine-tuned to remove standard safety alignment layers (guardrails) that limit a model's ability to discuss sensitive topics. Ollama offers
arXiv:2605.09507v1 Announce Type: new Abstract: Video summarization aims to produce a compact representation of a long video by selecting a subset of temporally important segments that best reflect hu
arXiv:2605.09276v1 Announce Type: cross Abstract: Spiking transformers have shown strong potential for neuromorphic vision, yet their token processing across multiple spiking steps still introduces su
arXiv:2505.22152v2 Announce Type: replace Abstract: While uncertainty estimation for graphs recently gained traction, most methods rely on homophily and deteriorate in heterophilic settings. We addres
arXiv:2605.09600v1 Announce Type: cross Abstract: Accurate skin lesion segmentation is vital for dermoscopic Computer-Aided Diagnosis. However, visual ambiguity and morphological irregularity often de
arXiv:2605.08575v1 Announce Type: cross Abstract: Mixture of Experts (MoE) architecture has become the standard for state-of-the-art large language models, owing to its computational efficiency throug
arXiv:2603.29002v2 Announce Type: replace-cross Abstract: Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse atte
arXiv:2605.08168v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models offer a promising path to generalist robot control, but their inference latency causes observation staleness when
arXiv:2511.12878v4 Announce Type: replace Abstract: Forecasting how human hands move in egocentric views is critical for applications like augmented reality and human-robot policy transfer. Recently,
arXiv:2605.10445v1 Announce Type: new Abstract: Unified Multimodal Models (UMMs) excel in general tasks but struggle to bridge the gap between personalized understanding and generation. Prior works la
arXiv:2605.09857v1 Announce Type: cross Abstract: Multicalibration requires predicted scores to agree with label probabilities across rich families of subgroups and score-dependent tests, but existing
arXiv:2605.08911v1 Announce Type: new Abstract: Autonomous vehicles need to perceive not only physical elements in the driving scene, such as lane lines and traffic lights, but also logical elements l
arXiv:2605.10821v1 Announce Type: new Abstract: Diffusion-based vision-language-action (VLA) models have emerged as strong priors for robotic manipulation, yet adapting them to real-world distribution
arXiv:2603.05301v2 Announce Type: replace Abstract: Inductive spatio-temporal kriging infers signals at unobserved locations from observed sensors, but real-world observations are often incomplete and
arXiv:2405.17642v3 Announce Type: replace-cross Abstract: The growing complexity of AI systems has intensified the need for transparency through Explainable AI (XAI). Counterfactual explanations (CFs)
arXiv:2605.05831v2 Announce Type: replace Abstract: The communication of scientific knowledge has become increasingly multimodal, spanning text, visuals, and speech through materials such as research
arXiv:2605.08709v1 Announce Type: new Abstract: Unified face attack detection (UAD) requires recognizing physical spoofing and digital forgery within a shared decision space, yet existing discriminati
arXiv:2605.08729v1 Announce Type: new Abstract: Motion, speech, and sound effects are fundamental elements of human-centric videos, yet their heterogeneous temporal characteristics make joint generati
arXiv:2603.07686v2 Announce Type: replace-cross Abstract: End-to-end (E2E) driving has become a cornerstone of both industry deployment and academic research, offering a single learnable pipeline that
arXiv:2605.09396v1 Announce Type: cross Abstract: This paper relaxes the restrictive symmetry conditions adopted in [4], [5] and extends their universal feature selection framework to accommodate nois
arXiv:2605.08765v1 Announce Type: cross Abstract: Unlearning in large language models (LLMs) aims to remove harmful training data while preserving overall utility. However, we find that existing metho
arXiv:2605.10083v1 Announce Type: new Abstract: Short-term air traffic flow prediction in terminal airspace is essential for proactive air traffic management. Existing approaches predominantly model t
arXiv:2605.10889v1 Announce Type: cross Abstract: On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this sign
arXiv:2605.09692v1 Announce Type: new Abstract: Unpredictable behavior is often taken as evidence of control, yet stochastic dispersion and structured action control need not coincide. This paper test
arXiv:2605.10158v1 Announce Type: new Abstract: Process Reward Models (PRMs) are a powerful mechanism for steering large language model reasoning by providing fine-grained, step-level supervision. How
arXiv:2605.10205v1 Announce Type: new Abstract: Decentralized stochastic gradient descent (D-SGD) is an efficient method for large-scale distributed learning. Existing generalization studies mainly ad
arXiv:2601.23273v2 Announce Type: replace Abstract: Prompt agents have recently emerged as a promising paradigm for automated prompt optimization, framing prompt discovery as a sequential decision-mak
arXiv:2603.03971v2 Announce Type: replace-cross Abstract: Generative AI can convert uncertainty into hypersuasive, authoritative-seeming verdicts, displacing the justificatory work on which democratic
arXiv:2605.09936v1 Announce Type: new Abstract: We present Urban-ImageNet, a large-scale multi-modal dataset and evaluation benchmark for urban space perception from user-generated social media imager
This discussion explores using Ollama to run large language models locally for invoice processing while maintaining control over data. The thread likely addresses selecting appropriate smaller models
arXiv:2605.10125v1 Announce Type: new Abstract: Artificial intelligence (AI) tools are being incorporated into scientific research workflows with the potential to enhance efficiency in tasks such as d
arXiv:2605.08766v1 Announce Type: cross Abstract: Personalized user understanding from large-scale digital traces remains a fundamental challenge. Traditional user profiling methods rely on discrimina
arXiv:2510.13830v2 Announce Type: replace-cross Abstract: Pairwise preference data have played an important role in the alignment of large language models (LLMs). Each sample of such data consists of
arXiv:2605.09769v1 Announce Type: new Abstract: This paper describes our system for classifying psychological defense mechanisms in emotional support dialogues using the Defense Mechanism Rating Scale
arXiv:2605.09040v1 Announce Type: new Abstract: Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-spec
arXiv:2605.10172v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a per
v0.30.0-rc15 is a release candidate version of Ollama, an open-source platform for running large language models locally. This particular release is part of the development cycle leading toward the st
arXiv:2605.10896v1 Announce Type: new Abstract: Corporate bankruptcy prediction is a high-stakes financial task characterized by severe class imbalance and multi-horizon forecasting demands. Public da
arXiv:2601.18823v3 Announce Type: replace Abstract: Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data. Once trained, one can h
arXiv:2605.10405v1 Announce Type: new Abstract: Selecting the best large language model (LLM) for a fixed benchmark is often expensive, since exhaustive evaluation requires running every model on ever