Knowledge catalogue
arXiv:2606.01861v1 Announce Type: new Abstract: Self-play, a type of training algorithm that enables a model to self-improve, has recently shown promising empirical results in the context of formal th
arXiv:2604.05324v2 Announce Type: replace Abstract: Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d. test data sampled from the ground-truth dist
arXiv:2511.19829v2 Announce Type: replace Abstract: Most prompt-optimization methods refine a single static template, making them ineffective in complex and dynamic user scenarios. Existing query-depe
arXiv:2506.10239v3 Announce Type: replace Abstract: Probabilistic Virtual Fixtures (VFs) enable the adaptive selection of the most suitable haptic feedback for each phase of a task, based on learned o
arXiv:2510.09288v2 Announce Type: replace-cross Abstract: The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge. Traditional defenses, such
arXiv:2606.02061v1 Announce Type: new Abstract: Dictionary learning with sparse autoencoders (SAEs) produces overcomplete bases from neural network activations that are often interpretable and reduces
arXiv:2606.01764v1 Announce Type: cross Abstract: We revisit the convergence guarantees of the Extragradient (EG) method for unconstrained biaffine min-max optimization. It is known that EG with a fix
arXiv:2606.00293v1 Announce Type: new Abstract: Tuning algorithms such as stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD) for approximate sampling and uncertainty qu
arXiv:2604.01562v2 Announce Type: replace-cross Abstract: Voice cloning is often evaluated in terms of overall quality, but less is known about accent preservation and its perceptual consequences. We
arXiv:2603.09692v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) has become the standard for aligning Large Language Models (LLMs), yet its efficacy is bottl
arXiv:2606.01367v1 Announce Type: cross Abstract: Active scene reconstruction enables robots/UAVs to autonomously plan trajectories and reconstruct environments without costly manual data acquisition.
arXiv:2606.02569v1 Announce Type: cross Abstract: Video is temporally redundant: adjacent frames usually share most objects, background, and layout. Yet existing video multimodal large language models
arXiv:2606.00141v1 Announce Type: cross Abstract: Adaptive sensing strategies that selectively sample data are increasingly used in wearable health systems to improve prediction performance under limi
arXiv:2606.01104v1 Announce Type: new Abstract: VRR-QA evaluates whether video-language systems can infer spatial, temporal, viewpoint, depth, and visibility relations that are not always resolved by
arXiv:2602.05139v3 Announce Type: replace Abstract: We study bandits whose rewards depend on an unobserved Markov state that evolves independently of the learner's actions. The optimal arm can change
arXiv:2606.00459v1 Announce Type: new Abstract: Compliant force or torque control are approaches often investigated to achieve safe physical human-robot interaction (pHRI). However, these approaches h
arXiv:2606.01827v1 Announce Type: cross Abstract: Sharpness-Aware Minimization (SAM) has established itself as a powerful and widely adopted optimizer for training machine learning models. By explicit
arXiv:2504.19419v3 Announce Type: replace Abstract: Local clustering aims to identify specific substructures within a large graph without any additional structural information of the graph. These subs
arXiv:2606.00093v1 Announce Type: new Abstract: Validating an LLM judge against human annotations usually means reporting several agreement statistics: accuracy, precision, recall, F_1, Cohen's kappa,
arXiv:2407.15510v2 Announce Type: replace Abstract: Abstraction is key to human and artificial intelligence as it allows one to identify common structure in otherwise distinct objects or situations. A
arXiv:2606.02163v1 Announce Type: new Abstract: This article proposes a set-theoretic framework for belief change, called Abstract Worlds Semantics, in which no logical syntax is assumed. Inspired by
arXiv:2606.00640v1 Announce Type: new Abstract: A new framework for the estimation of the complexity posed by video-question pairs to video-LLMs, Video Attribute-Based Complexity (VideoABC), is propos
arXiv:2606.00522v1 Announce Type: new Abstract: In this work, we present our solution for the 8th UG2+ Challenge (CVPR 2026) Track 3: Dynamic Object Segmentation in Turbulence (DOST). Our method is bu
arXiv:2606.01217v1 Announce Type: new Abstract: Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by challenges in communication and behavior. This study examines the relat
arXiv:2606.01053v1 Announce Type: new Abstract: Editing complex, long-form knowledge in Large Language Models remains a significant challenge due to the difficulty of maintaining generation coherence.
arXiv:2606.01736v1 Announce Type: cross Abstract: As LLMs are increasingly used to draft public-facing arguments, they may flatten public debate by repeatedly introducing the same polished, plausible
arXiv:2606.00024v1 Announce Type: new Abstract: Long-context decoding in Large Language Models (LLMs) is severely constrained by the memory bandwidth required to fetch the extensive Key-Value (KV) cac
arXiv:2601.19919v2 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is one of the most effective paradigms for compressing large-scale foundation models into deployable architectures
arXiv:2606.01558v1 Announce Type: new Abstract: The effectiveness of Chain-of-Thought (CoT) prompting in Multimodal Large Language Models (MLLMs) remains uncertain: across several visual reasoning ben
arXiv:2606.00414v1 Announce Type: new Abstract: When many reinforcement-learning policies achieve near-optimal return, a post-hoc auditor may have to distinguish among many behaviorally distinct but r
arXiv:2606.01006v1 Announce Type: new Abstract: Capillary-level retinal blood flow (RBF) has strong potential as a biomarker for various ocular diseases. However, modalities for measuring capillary-le
arXiv:2606.00130v1 Announce Type: cross Abstract: We study Automatically Differentiable Nonlinear Tensor Networks (ADNTNs), a family of structured weight generators whose compact core tensors are trai
arXiv:2601.00664v2 Announce Type: replace-cross Abstract: Talking head generation creates lifelike avatars from static portraits for virtual communication and content creation. However, current models
arXiv:2511.20295v2 Announce Type: replace Abstract: Counterfactual explanations (CFEs) are minimal and semantically meaningful modifications of the input of a model that alter the model predictions. T
arXiv:2606.01906v1 Announce Type: new Abstract: Emotions evolve through the dynamics of conversation, and understanding their transition structure is foundational to applications ranging from mental-h
arXiv:2606.00709v1 Announce Type: new Abstract: Visual-Inertial Odometry (VIO) provides smooth, high-rate state estimates and has been widely used for robotic navigation in both terrestrial and planet
arXiv:2606.00180v1 Announce Type: cross Abstract: Deep learning-based Major Depressive Disorder (MDD) detection using Electroencephalography (EEG) is fundamentally constrained by the 'small-sample dil
arXiv:2505.18113v2 Announce Type: replace Abstract: Training quantized neural networks requires addressing the non-differentiable and discrete nature of the underlying optimization problem. To tackle
arXiv:2606.01945v1 Announce Type: new Abstract: Visual Prompting (VP) has emerged as an efficient paradigm for adapting large-scale pre-trained vision models to downstream tasks by incorporating learn
arXiv:2507.15336v3 Announce Type: replace-cross Abstract: Designing high-performance neural networks for new tasks requires balancing optimization quality with search efficiency. Current methods fail
arXiv:2510.24078v2 Announce Type: replace Abstract: Text-to-image (T2I) models are increasingly used for synthetic dataset generation, but generating effective synthetic training data for classificati
arXiv:2606.01258v1 Announce Type: cross Abstract: Standard positional encodings for transformers - sinusoidal and rotary (RoPE) - treat every position as equally local: they encode where a token is, b
arXiv:2603.18652v2 Announce Type: replace-cross Abstract: Reliably extracting tables from PDFs is essential for large-scale scientific data mining and knowledge base construction, yet existing evaluat
arXiv:2606.01095v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies and World-Action Models (WAM) represent two increasingly important paradigms for robotic manipulation. However,
arXiv:2606.00670v1 Announce Type: cross Abstract: Face-to-face speech comprehension is inherently multimodal, integrating acoustic signals with visible articulation, facial expression, head motion, an
arXiv:2509.06948v3 Announce Type: replace Abstract: Supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) are two widely used post-training paradigms for improving the
arXiv:2606.01287v1 Announce Type: cross Abstract: Recent latent visual reasoning methods achieve substantial gains by inserting continuous latent tokens into multimodal language models. These gains ar
arXiv:2606.00079v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-inte
arXiv:2606.02241v1 Announce Type: new Abstract: Is the uniform-state diffusion framework a more powerful paradigm for discrete diffusion? Recent studies indicate that this may be the case. In combinat
arXiv:2606.01856v1 Announce Type: cross Abstract: Multimodal Federated Learning (MMFL) enables privacy-preserving collaborative learning across decentralized clients with heterogeneous data and modali
arXiv:2012.01494v2 Announce Type: replace Abstract: Braille is the only system to visually impaired people for reading and writing. However, general people cannot read Braille. So, teachers and relati
arXiv:2606.01237v1 Announce Type: new Abstract: Mild cognitive impairment (MCI) and subjective cognitive decline (SCD) are closely associated with the early Alzheimer's disease continuum, where accura
arXiv:2606.00095v1 Announce Type: cross Abstract: Vision-Language Navigation (VLN) enables embodied agents to reach target locations in unseen environments by following language instructions. Despite
arXiv:2509.23782v4 Announce Type: replace Abstract: While large language models (LLMs) perform strongly on diverse tasks, their trustworthiness is limited by erratic behavior that is unfaithful to the
arXiv:2606.00927v1 Announce Type: new Abstract: Accurate brain tumor classification from magnetic resonance imaging (MRI) is a key requirement for early diagnosis and clinical decision-making. Vision
arXiv:2505.14411v4 Announce Type: replace Abstract: Existing time series tokenization methods predominantly encode a constant number of samples into individual tokens. This inflexible approach can gen
arXiv:2606.01182v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at static reasoning tasks, yet their performance often degrades in interactive scenarios where information must be
arXiv:2606.00089v1 Announce Type: cross Abstract: Predictive Physical AI systems output state rollouts, action chunks, and latent plans, yet a low root-mean-square error (RMSE) does not imply that a p
arXiv:2606.01695v1 Announce Type: new Abstract: Adversaries can implant latent harmful behavior by poisoning as few as 1% of fine-tuning examples. The contamination is invisible to every output-level
arXiv:2606.00426v1 Announce Type: new Abstract: Federated continual learning (FCL) lets distributed clients adapt language-model heads to evolving NLP tasks without sharing raw text. Under user-level