Knowledge catalogue
arXiv:2610.21095v1 Announce Type: new Abstract: World and action modeling are closely related, yet their reciprocal benefits under unified causal training remain unclear. We introduce OneWM, a simple
arXiv:2610.21151v1 Announce Type: cross Abstract: Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured by conventional technical ass
arXiv:2610.20668v1 Announce Type: cross Abstract: We introduce CascadeLedger, a counterfactual execution-audit framework for budgeted language-model cascades. The protocol enforces call-before-read se
arXiv:2610.22292v1 Announce Type: cross Abstract: Large language models (LLMs) are becoming prevalent in scenarios where honesty is critical. However, despite alignment training, these models still ex
arXiv:2610.20750v1 Announce Type: new Abstract: Vision-language-action (VLA) models are a promising approach to general purpose robot manipulation. While the internal computation of vision-language mo
arXiv:2610.22126v1 Announce Type: cross Abstract: Existing feature attribution methods that account for feature dependencies do not scale to high dimensions. We propose causal integrated gradients (CI
arXiv:2607.18921v2 Announce Type: replace-cross Abstract: Circuit extraction identifies model components whose presence preserves a target behavior under ablation, but preserving behavior does not sin
arXiv:2610.21409v1 Announce Type: new Abstract: Traditional keypoint descriptors, such as SIFT (Scale-Invariant Feature Transform) and ORB (Oriented FAST and Rotated BRIEF), are computed from local im
arXiv:2610.21804v1 Announce Type: new Abstract: Incremental learning (IL) aims to continually acquire new knowledge (plasticity) while retaining previously learned information (stability). However, st
arXiv:2610.21364v1 Announce Type: new Abstract: One-shot Font Generation (OFG) aims to synthesize a target glyph by transferring the stylistic characteristics of a single reference glyph while preserv
arXiv:2610.20877v1 Announce Type: cross Abstract: Early detection of mild cognitive impairment remains a critical bottleneck in dementia care, demanding scalable tools capable of capturing subtle beha
arXiv:2610.21126v1 Announce Type: new Abstract: Sparse KV compression reduces long-context inference costs by retaining selected historical states, yet these states typically keep their coordinates fr
arXiv:2610.21195v1 Announce Type: new Abstract: On-policy distillation (OPD) improves a student language model by training on its own generated trajectories with supervision from a stronger teacher. H
arXiv:2610.20828v1 Announce Type: cross Abstract: Reasoning distillation requires chain-of-thought (CoT) data with correct answers, but obtaining such data efficiently remains challenging. Forward CoT
arXiv:2610.20679v1 Announce Type: new Abstract: Representation-based safety defenses for vision-language models (VLMs) often learn to separate harmful from benign inputs, but separation alone does not
arXiv:2610.21321v1 Announce Type: new Abstract: Although Graph Neural Networks are widely used in various domains, they remained mostly unexplored in computer vision. Convolutional Neural Networks and
arXiv:2610.21470v1 Announce Type: new Abstract: When a vision-language model is finetuned on class-imbalanced data, rare-class recall can fall well below the model's own zero-shot performance. In this
arXiv:2610.21681v1 Announce Type: new Abstract: Data strategy plays a central role in training large language models (LLMs). It governs the selection, weighting, and scheduling of training data, there
Today, Reflection released Beam, its first open-weight model built to give developers, researchers, and enterprises open control and customization for frontier software engineering and long-horizon ag
arXiv:2610.22201v1 Announce Type: cross Abstract: We present a scalable framework for solving multi-step tasks through a decentralized market of self-interested agents. Prior theoretical work demonstr
arXiv:2610.20922v1 Announce Type: new Abstract: Compositional structure is pervasive in nature and across scales: atoms combine into molecules, molecules into cells, and cells into organisms, while fu
arXiv:2610.22325v1 Announce Type: new Abstract: Reconstructing human motion in 4D requires identifying the same surface points through articulation, deformation and changes in visibility. We introduce
arXiv:2610.21639v1 Announce Type: new Abstract: Ensemble weather forecasts can look reliable in global averages while hiding too little spread in some cases and too much in others. These errors vary a
arXiv:2506.03467v4 Announce Type: replace-cross Abstract: Gaussian Mixture Models (GMMs) are widely used statistical models for representing multi-modal data distributions, with numerous applications
arXiv:2610.21654v1 Announce Type: new Abstract: This paper presents the Digital Typhoon Dataset V3, a new version of the longest typhoon satellite image dataset spanning nearly 50 years, designed to b
arXiv:2610.21340v1 Announce Type: cross Abstract: Classical PAC-Bayesian generalization theory places prior distributions over Euclidean parameter space Theta subseteq R^D, causing relative entropy to
arXiv:2610.20680v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are typically trained on hundreds of millions to billions of activation tokens, yet little work has tested whether this scale
arXiv:2610.21281v1 Announce Type: new Abstract: Root-cause analysis (RCA) in large-scale distributed systems is challenging because a single symptom can cross service, data, configuration, compute, an
arXiv:2610.21215v1 Announce Type: new Abstract: Reliable image geometric estimation from noisy matching points is typically addressed using RANSAC, often combined with local optimization to refine inl
arXiv:2610.21424v1 Announce Type: new Abstract: Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Repres
arXiv:2610.21337v1 Announce Type: cross Abstract: On-policy distillation (OPD) effectively transfers capabilities from a teacher to a student through feedback on student-generated rollouts. However, g
arXiv:2610.20652v1 Announce Type: new Abstract: Always-on virtual assistants increasingly personalize on-device to new user-specific commands via few-shot fine-tuning (e.g., LoRA), but this adaptation
arXiv:2610.22130v1 Announce Type: new Abstract: Key-value (KV) cache management has become a critical bottleneck for scaling Large Language Models (LLMs) to long-context scenarios due to linear memory
arXiv:2610.21467v1 Announce Type: cross Abstract: Transcribing expressive piano performances into scores requires interpreting individual note timings within an underlying metrical structure. However,
arXiv:2610.21644v1 Announce Type: cross Abstract: Pairwise Difference Learning for Classification (PDC) enhances supervised learning in low-data regimes by training a binary similarity classifier on p
arXiv:2610.20904v1 Announce Type: cross Abstract: Egocentric human videos offer a scalable alternative to costly robot demonstra- tions, yet transferring their manipulation priors to robot control rem
arXiv:2610.21347v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly operate in multi-turn interactions that require maintaining latent conversational states, not only explicit fa
arXiv:2610.21713v1 Announce Type: cross Abstract: Language embeddings are increasingly used in recommenders to represent item content, but their privacy risks remain poorly understood. We study whethe
arXiv:2610.21671v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves multimodal reasoning, but group-relative policy optimization broadcasts a single sequence
arXiv:2610.21204v1 Announce Type: new Abstract: When a speaker says ``some students passed'', listeners infer that not all of them did. Reasoning models now let users decide how long a model thinks be
arXiv:2610.21368v1 Announce Type: cross Abstract: With the expansion of pre-trained language model usage in recent years, the importance of datasets for performing tasks in specialized domains has sig
arXiv:2610.22035v1 Announce Type: cross Abstract: Current heterogeneity-aware training systems for large models balance workloads by assigning unequal numbers of layers across pipeline stages, a strat
arXiv:2610.22186v1 Announce Type: cross Abstract: Recent advances in Omni Language Models (OLMs) provide a unified solution for audiovisual video captioning. Nevertheless, existing approaches predomin
arXiv:2610.21180v1 Announce Type: new Abstract: General-purpose dexterous manipulation requires policies to transfer knowledge from related tasks to new tasks with only a few target demonstrations. Ex
arXiv:2610.21018v1 Announce Type: new Abstract: When every rollout for a problem fails, GRPO receives neither a successful exemplar nor a nonzero group-relative advantage, so it learns nothing from ex
arXiv:2610.21389v1 Announce Type: new Abstract: Vision-language-action (VLA) policies commonly place a multi-billion-parameter model inside the feedback loop, repeatedly recomputing task context whene
arXiv:2610.22146v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models present a promising paradigm for general-purpose robot manipulation, but closed-loop deployment is often limited by
arXiv:2610.21402v1 Announce Type: new Abstract: Optical Wireless Communication (OWC) systems provide high-bandwidth, spatially secure, and RF-interference-free digital transmission. However, direct fr
arXiv:2610.21547v1 Announce Type: new Abstract: Federated learning (FL) is increasingly used to adapt a pretrained, centrally fine-tuned model to data that remain on user devices, beyond training a mo
arXiv:2610.21246v1 Announce Type: new Abstract: Large language model (LLM)-guided Bayesian optimization (BO) uses past observations to guide search, but proposed directions and their revision can rema
arXiv:2610.21250v1 Announce Type: new Abstract: Multi-teacher on-policy distillation enables rectified-flow models with diffusion-transformer architectures to combine task-specific capabilities within
arXiv:2610.20918v1 Announce Type: cross Abstract: Utilities request mutual aid crews to restore power after severe storms, and requesting early secures more crews but relies on less accurate forecasts
arXiv:2610.21165v1 Announce Type: new Abstract: Long-context capability has become essential for large language models (LLMs) to handle complex tasks, yet continuously expanding the context window doe
arXiv:2610.21452v1 Announce Type: cross Abstract: Human face-to-face conversation requires coordinating speech, gestures and expressions across both speaking and listening. We present ELLSA 2, an end-
arXiv:2610.20655v1 Announce Type: cross Abstract: We present a global-in-time spectral Duhamel-Picard method with polynomial expansions for post-exposure bake (PEB) simulation. The coupled acid-quench
arXiv:2610.21892v1 Announce Type: new Abstract: We propose the Graph Dirichlet Energy Causal Inference (GDECI) criterion for distinguishing cause from effect in bivariate settings. For a candidate dir
arXiv:2610.22031v1 Announce Type: new Abstract: Behavioral consistency across repeated executions provides an informative signal for assessing the reliability of large language model (LLM) agents. How
arXiv:2610.22014v1 Announce Type: cross Abstract: Longitudinal electronic health records (EHRs) contain complementary diagnostic and laboratory information about patient health. However, irregularity,
arXiv:2610.22312v1 Announce Type: new Abstract: Spatial instructions describe how to move objects, transform regions, or modify their surroundings. When several operations are applied in sequence, eac
arXiv:2610.22360v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) and 3D generation have expanded 3D understanding and synthesis. However, beyond visual fidel