Knowledge catalogue
arXiv:2607.19077v1 Announce Type: new Abstract: Training video anomaly detectors is challenging due to the difficulty and cost of annotating diverse and rare abnormal events. Although recent large vis
arXiv:2404.00491v3 Announce Type: replace Abstract: Physically-based renderings contain Monte Carlo noise, with variance that increases as the number of rays per pixel decreases. This noise, while zer
arXiv:2607.19367v1 Announce Type: new Abstract: Calibration is the primary criterion for evaluating LLM confidence, but it is insufficient: it admits trivially incoherent estimators, depends on the ev
arXiv:2607.20274v1 Announce Type: cross Abstract: Medical image encoders from different groups are increasingly treated as interchangeable, on the assumption that scale and clinical supervision concen
arXiv:2607.12463v1 Announce Type: new Abstract: Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in
arXiv:1809.01898v2 Announce Type: replace-cross Abstract: The growing complexity of software calls for innovative solutions that support the deployment of reliable and secure software. Machine Learnin
arXiv:2607.12616v1 Announce Type: new Abstract: Continuous-time generative frameworks construct probability paths between base and target domains by optimizing time-dependent velocity fields. While th
arXiv:2607.08436v1 Announce Type: cross Abstract: Egocentric human data offers scalable supervision for robot manipulation. However, behavior cloning entangles transferable content like objects, scene
arXiv:2607.08003v1 Announce Type: cross Abstract: Catalysts are essential for sustainable chemical manufacturing, yet discovering novel architectures remains a bottleneck dominated by trial-and-error
arXiv:2607.02300v2 Announce Type: replace Abstract: In the automotive domain, in-car scene understanding (ISU) enables the detection of safety-critical events, such as driver distraction, and supports
arXiv:2607.06833v1 Announce Type: new Abstract: Sampling stochastic signals supported on a graph underlies many graph machine learning tasks, including recommender systems, forecasting in financial ma
arXiv:2607.07375v1 Announce Type: cross Abstract: Adversarial vulnerability in deep neural networks (DNNs) has been studied from the perspectives of decision-boundary geometry, feature robustness, inp
arXiv:2607.05702v1 Announce Type: new Abstract: Images acquired in surveillance environments often suffer from conditions such as low resolution, variations in pose, irregular illumination, and occlus
arXiv:2512.18542v3 Announce Type: replace-cross Abstract: AI coding assistants produce vulnerable code in 45% of security-relevant scenarios~ite{veracode2025}, yet no public training dataset teaches b
arXiv:2607.02959v1 Announce Type: new Abstract: We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-t
arXiv:2607.04277v1 Announce Type: cross Abstract: The pursuit of self-evolving AI raises a critical question: when is autonomous self-improvement sustainable rather than degenerative? Drawing an analo
Every year, the International Conference on Machine Learning (ICML) reveals where thousands of AI researchers have decided to put their work. This year’s accepted papers reveal a clear direction: open
In this post, we introduce Reverse Direct Preference Optimization (rDPO), the novel unlearning technique behind Amazon Nova Customizable Content Moderation Settings (CCMS), and show how it reduces ove
arXiv:2510.20692v2 Announce Type: replace-cross Abstract: Cloud computing is ubiquitous, with a growing number of services being hosted on the cloud every day. Typical cloud compute systems allow admi
arXiv:2607.02491v1 Announce Type: new Abstract: In this work, we focus on SE-RRMs, a symbol-equivariant instantiation of RRMs that exhibits improved extrapolation to larger problem sizes. We propose a
arXiv:2607.02369v1 Announce Type: cross Abstract: LLMs stage a new form of cultural encounter that is massive, automated, and monolingual. Literary disciplines have always negotiated cultural struggle
arXiv:2607.00946v1 Announce Type: cross Abstract: While prior work has explored emotion control in hybrid text-to-speech systems, the geometric properties of these modules, and their implications for
arXiv:2607.00357v1 Announce Type: new Abstract: Personalized object localization (POL) localizes an object instance in a query image based on a few reference images with bounding-box annotations and a
arXiv:2606.31577v1 Announce Type: new Abstract: Conformal predictions have attracted significant attention in the field of uncertainty quantification, mainly because of their strong marginal coverage
arXiv:2511.12309v2 Announce Type: replace-cross Abstract: Self-consistency (SC) is a widely used test-time inference technique for improving performance in chain-of-thought reasoning. It consists of g
arXiv:2606.31976v1 Announce Type: new Abstract: Human-labeled data are widely used as reference annotations in ML, despite known variability across annotators in many expert-driven domains. In additio
arXiv:2604.03316v2 Announce Type: replace Abstract: Attention sinks are defined as tokens that attract disproportionate attention. While these have been studied in single modality transformers, their
arXiv:2606.28708v1 Announce Type: new Abstract: Accurately explaining hidden patterns in multi-aspect data has typically been done by leveraging labels and/or accompanying auxiliary metadata. However,
arXiv:2407.02351v3 Announce Type: replace Abstract: The rapid spread of false and misleading information on online platforms poses a growing societal challenge, overwhelming the capacity of manual fac
arXiv:2606.30460v1 Announce Type: new Abstract: In this paper, we aim to combine the advantages of existing sequence parallelism paradigms and overcomes their drawbacks, the most serious of which is t
arXiv:2603.18907v2 Announce Type: replace Abstract: We propose a new Neural Galerkin Normalizing Flow framework to approximate the transition probability density function of a diffusion process by sol
arXiv:2502.19460v4 Announce Type: replace-cross Abstract: Dependent censoring occurs when the event time and censoring time are not conditionally independent given the observed covariates. This compli
arXiv:2606.28760v1 Announce Type: new Abstract: Social robot navigation (SRN) requires more than geometric path planning; it demands understanding human intentions, social norms, and contextual cues t
arXiv:2606.13670v2 Announce Type: replace Abstract: Reproducibility in the social and behavioral sciences is typically evaluated by independent researchers who reanalyze the original data to assess wh
arXiv:2606.26593v1 Announce Type: new Abstract: Email communication has become an integral part of personal and professional life, but handling its vast volume is still a significant issue for large o
arXiv:2606.26366v1 Announce Type: new Abstract: Standard chain-of-thought on moral dilemmas exhibits two failure modes: stakeholder collapse (the trace names at most one party with a stake in the outc
arXiv:2602.01969v2 Announce Type: replace Abstract: Complex tables with multi-level headers, merged cells and heterogeneous layouts pose persistent challenges for LLMs in both understanding and reason
arXiv:2504.09910v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) is a promising technique for applying LLMs to proprietary domains. However, retrieved documents may contain sen
arXiv:2602.05704v2 Announce Type: replace Abstract: Understanding the limitations of gradient methods, and stochastic gradient descent (SGD) in particular, is a central challenge in learning theory. T
arXiv:2606.24985v1 Announce Type: new Abstract: Personalization in wearable-based stress detection remains challenging due to substantial inter-individual variability in physiological and behavioral r
arXiv:2606.20880v1 Announce Type: cross Abstract: Decision-making under partial or adversarial observability requires accurate inference of the environment's latent state and its associated uncertaint
arXiv:2505.11495v2 Announce Type: replace Abstract: Push recovery during locomotion will facilitate the deployment of humanoid robots in human-centered environments. In this paper, we present a unifie
arXiv:2606.21773v1 Announce Type: new Abstract: Plugging predictions of unknown parameters into downstream optimization problems, often referred to as the ``predict-then-optimize'' paradigm, has long
arXiv:2606.22702v1 Announce Type: new Abstract: Traditional supervised methods for structured visual recognition tasks -- such as object detection, segmentation, and scene graph generation -- often pr
arXiv:2606.22460v1 Announce Type: cross Abstract: Music streaming services such as Deezer often recommend personalized playlists to users. Playlist captioning, which involves describing these playlist
arXiv:2603.07307v2 Announce Type: replace Abstract: Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-atten
arXiv:2606.22729v1 Announce Type: new Abstract: Diffusion policies enable multimodal robot behavior but offer limited ability to choose among behavior modes at inference time, even though such control
OpenCodeRAG is a local embedding service using FastAPI and SentenceTransformer, paired with a Node.js plugin that integrates RAG tools with Qdrant vector database via YAML configuration. It provides a
arXiv:2606.10495v1 Announce Type: new Abstract: Safe social navigation requires robots to distinguish people from ordinary obstacles and to react before danger becomes imminent. We show that pretraine
arXiv:2509.16518v2 Announce Type: replace Abstract: Using diffusion transformers for media generation may require evaluating attention over extremely long sequences, with attention layers accounting f
arXiv:2606.10046v1 Announce Type: cross Abstract: Flow-matching transformers achieve strong audio separation, yet their attention dynamics are opaque. We adapt established causal-intervention principl
arXiv:2606.10971v1 Announce Type: new Abstract: Precise state estimation for navigation of autonomous agricultural robots is often compromised by sensor outages (GNSS/LiDAR/Visual) and high-frequency
arXiv:2411.16102v2 Announce Type: replace Abstract: Offline batch inference, which leverages the flexibility of request batching to achieve higher throughput and lower costs, is becoming more popular
arXiv:2508.11874v2 Announce Type: replace-cross Abstract: Designing polynomial-time algorithms for approximate Nash equilibria (ANE) with provable worst-case guarantees is a fundamental open problem i
arXiv:2603.10395v2 Announce Type: replace Abstract: Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, aka
arXiv:2606.07690v1 Announce Type: cross Abstract: Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repea
arXiv:2510.09783v2 Announce Type: replace-cross Abstract: Oversampling is one of the most widely used approaches for addressing imbalanced classification. The core idea is to generate additional minor
arXiv:2606.09701v1 Announce Type: cross Abstract: AI red teaming must continually adapt to evolving attackers and defenders. Reinforcement learning offers a promising approach to discovering novel att
arXiv:2606.07589v1 Announce Type: new Abstract: Sequential filtering pipelines are a common design pattern in large-scale systems, where a large population of items is progressively reduced by a seque
arXiv:2606.07676v1 Announce Type: cross Abstract: Spatial transcriptomics (ST) is a powerful tool for exploring biological properties dependent on structure, proximity, and interaction in tissue. The