Knowledge catalogue
arXiv:2602.13215v2 Announce Type: replace Abstract: Recurrent-attention hybrids aim to combine the efficiency of recurrence with the expressivity of attention, but existing approaches typically apply
arXiv:2605.12774v1 Announce Type: new Abstract: Estimating camera pose in dynamic environments is a critical challenge, as most visual SLAM and SfM methods assume static scenes. While recent dynamic-a
arXiv:2605.11367v1 Announce Type: new Abstract: Recent advances in visual generative models have highlighted the promise of learning generative world models. However, most existing approaches frame wo
arXiv:2605.12027v1 Announce Type: new Abstract: Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric
arXiv:2605.11406v1 Announce Type: new Abstract: Existing granular-ball classification methods are often driven by handcrafted quality measures, neighborhood rules, or heuristic splitting and stopping
arXiv:2605.11010v1 Announce Type: new Abstract: Federated Learning has emerged as a transformative paradigm for collaborative machine learning across distributed environments. However, its performance
A lot of people have been wondering about Mythos, Glasswing, and the vulns we / our partners are fixing. Today, I’m excited for us to start sharing more. (For context, I lead Glasswing @AnthropicAI.)
arXiv:2605.12350v1 Announce Type: new Abstract: Lack of transparency in AI systems poses challenges in critical real-life applications. It is important to be able to explain the decisions of an AI sys
arXiv:2605.11513v1 Announce Type: new Abstract: Knowledge Distillation (KD) is a critical tool for training Large Language Models (LLMs), yet the majority of research focuses on approaches that rely s
arXiv:2211.03524v2 Announce Type: replace Abstract: Modern Review Helpfulness Prediction systems are dependent upon multiple modalities, typically texts and images. Unfortunately, those contemporary a
arXiv:2605.11880v1 Announce Type: new Abstract: TD(lambda) in value-based MARL algorithms or the Temporal Difference critic learning in Actor-Critic-based (AC-based) algorithms synergistically integra
arXiv:2605.11727v1 Announce Type: cross Abstract: Vision-language models typically reason over post-ISP RGB images, although RGB rendering can clip, suppress, or quantize sensor evidence before infere
arXiv:2605.12495v1 Announce Type: new Abstract: In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models
arXiv:2605.11378v1 Announce Type: new Abstract: Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive
arXiv:2605.12069v1 Announce Type: new Abstract: Zero-shot anomaly detection aims to identify defects in unseen categories without target-specific training. Existing methods usually apply the same feat
arXiv:2605.11609v1 Announce Type: cross Abstract: On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedbac
arXiv:2604.04894v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of large language models (LLMs), but it often
arXiv:2605.11014v1 Announce Type: new Abstract: Fair comparison between diffusion-based OOD detectors is challenging, as conclusions can vary with backbone choice, corruption parameterization, and tes
arXiv:2605.12413v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) show strong visual perception, yet remain limited in reasoning about space under changing viewpoints. We study
arXiv:2605.11460v1 Announce Type: new Abstract: System identification (SysID) is critical for modeling dynamical systems from experimental data, yet traditional approaches often fail to capture nonlin
arXiv:2605.11287v1 Announce Type: new Abstract: A persistent paradox in time-series forecasting is that structurally simple MLP and linear models often outperform high-capacity Transformers. We argue
arXiv:2605.11829v1 Announce Type: cross Abstract: The accurate recovery of constituent-level optical properties from integrating sphere measurements is a central analytical challenge in pharmaceutical
arXiv:2605.11461v1 Announce Type: cross Abstract: Reinforcement learning with verifiers (RLVR) has become a central paradigm for improving LLM reasoning, yet popular group-based optimization algorithm
arXiv:2605.12339v1 Announce Type: new Abstract: Aligning language models for both helpfulness and safety typically requires complex pipelines-separate reward and cost models, online reinforcement lear
arXiv:2605.11723v1 Announce Type: new Abstract: In this paper, we propose Concentrate and Concentrate (CaC), a coarse-to-fine anomaly reward model based on Vision-Language Models. During inference, it
arXiv:2605.12266v1 Announce Type: new Abstract: Graph-based machine learning has emerged as a promising approach for manufacturability analysis by learning directly from CAD models represented as Boun
arXiv:2605.11186v1 Announce Type: new Abstract: Auto-regressive decoding in Large Language Models (LLMs) is inherently memory-bound: every generation step requires loading the model weights and interm
clarifying how much “task horizon” falls off as a function of the increasing accuracy criterion directly in the graph (not across tabs) would definitely improve this graph, @METR_Evals. as a variant o
arXiv:2509.20899v3 Announce Type: replace Abstract: Concept Bottleneck Models (CBMs) enable interpretable image classification by structuring predictions around human-understandable concepts, but exte
arXiv:2605.11159v1 Announce Type: new Abstract: Knowledge graph completion (KGC) aims to automatically infer missing facts in multi-relational data by mapping entities and relations into continuous re
arXiv:2605.11165v1 Announce Type: new Abstract: Federated learning (FL) in heterogeneous environments remains challenging because client models often differ in both architecture and data distribution.
arXiv:2603.28488v2 Announce Type: replace Abstract: Large language models (LLMs) remain unreliable for high-stakes claim verification due to hallucinations and shallow reasoning. While retrieval-augme
arXiv:2605.11784v1 Announce Type: cross Abstract: Full-vehicle crash simulations are computationally expensive, limiting their use in iterative design exploration. This work investigates learned hybri
arXiv:2605.12145v1 Announce Type: new Abstract: Multimodal learning seeks to integrate information across diverse sensory sources, yet current approaches struggle to balance cross-modal generalizabili
arXiv:2605.11260v1 Announce Type: new Abstract: Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models.
arXiv:2605.11711v1 Announce Type: new Abstract: Model-based representations recently stand out as a promising framework that embeds latent dynamics information into the representations for downstream
arXiv:2605.11237v1 Announce Type: new Abstract: Despite the burgeoning body of work on distribution shifts, provenance shift-where the relationship between data source and label changes at deployment-
arXiv:2605.11388v1 Announce Type: new Abstract: Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity t
arXiv:2510.27055v2 Announce Type: replace Abstract: We present Contamination Detection via Context (CoDeC), a practical and accurate method to detect and quantify training data contamination in large
arXiv:2304.09479v5 Announce Type: replace Abstract: We introduce a novel approach to single-view face relighting in the wild, addressing challenges such as global illumination and cast shadows. A comm
arXiv:2605.11601v1 Announce Type: new Abstract: Autoregressive language models are widely used for text evaluation, however, their left-to-right factorization introduces positional bias, i.e., early t
arXiv:2602.06462v3 Announce Type: replace Abstract: Masked diffusion language models generate text through iterative masked-token filling, but terminal-only rewards on final completions provide coarse
arXiv:2605.11210v1 Announce Type: new Abstract: We present a framework for distributed Pose Graph Optimization (PGO) by formulating the problem as a second-order continuous-time dynamical system evolv
arXiv:2605.12178v1 Announce Type: cross Abstract: World models enable agents to anticipate the effects of their actions by internalizing environment dynamics. In enterprise systems, however, these dyn
arXiv:2605.11683v1 Announce Type: new Abstract: Vision Transformers (ViTs) incur significant computational overhead due to the quadratic complexity of self-attention relative to the token sequence len
arXiv:2605.11750v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are often brittle in fine-grained manipulation, where minor action errors during the critical phases can rapidly e
arXiv:2605.12183v1 Announce Type: new Abstract: Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference. The premise
arXiv:2605.11567v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models predominantly adopt action chunking, i.e., predicting and committing to a short horizon of consecutive low-level act
arXiv:2605.11480v1 Announce Type: new Abstract: Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Am
arXiv:2605.12019v1 Announce Type: new Abstract: Human Activity Recognition (HAR) is a core task in pervasive computing systems, where models must operate under strict computational constraints while r
arXiv:2605.12297v1 Announce Type: new Abstract: Egocentric 3D hand pose estimation and gesture recognition are essential for immersive augmented/virtual reality, human-computer interaction, and roboti
arXiv:2605.12498v1 Announce Type: new Abstract: Reconstructing the absolute 3D pose and shape of the hands from the user's viewpoint using a single head-mounted camera is crucial for practical egocent
arXiv:2605.11775v1 Announce Type: cross Abstract: Policy entropy has emerged as a fundamental measure for understanding and controlling exploration in reinforcement learning with verifiable rewards (R
arXiv:2605.11328v1 Announce Type: new Abstract: Automated scientific discovery using large language models relies on identifying genuinely novel solutions. Standard reinforcement learning penalizes hi
arXiv:2605.11524v1 Announce Type: new Abstract: Data-driven identification of partial differential equations (PDEs) relies on sparse regression over a candidate library of differential operators, wher
arXiv:2605.12388v1 Announce Type: cross Abstract: Effective multi-agent cooperation requires agents to adopt diverse behaviors as task conditions evolve-and to do so at the right moment. Yet, current
arXiv:2605.11607v1 Announce Type: cross Abstract: Probabilistic partial least squares (PPLS) is a central likelihood-based model for two-view learning when one needs both interpretable latent factors
arXiv:2605.11428v1 Announce Type: new Abstract: Exploratory analysis of high-dimensional data rarely stops at a single embedding. In practice, analysts rerun dimensionality reduction after changing pr
arXiv:2605.11815v1 Announce Type: new Abstract: Hierarchical federated learning (HFL) leverages edge servers for partial aggregation in edge computing. Yet existing FL methods lack mechanisms for join
arXiv:2605.11403v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, with Group Relative Policy Opti