Knowledge catalogue
arXiv:2604.17738v1 Announce Type: new Abstract: Candidate sourcing for recruiters is best viewed as a two-stage retrieval and reranking pipeline with recall as the primary objective under a limited re
arXiv:2602.16144v3 Announce Type: replace Abstract: As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical
arXiv:2512.21510v2 Announce Type: replace-cross Abstract: Real-world multi-view data often exhibit highly inconsistent missing patterns, posing significant challenges for incomplete multi-view cluster
arXiv:2604.17982v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) still struggle with vision hallucination, where generated responses are inconsistent with the visual input. Exist
arXiv:2604.18087v1 Announce Type: new Abstract: Topic-controlled summarisation enables users to generate summaries focused on specific aspects of source documents. This paper investigates a data augme
arXiv:2603.23868v2 Announce Type: replace Abstract: In this paper, we address the challenging problem of single-scene, fully unsupervised video anomaly detection (VAD), where raw videos containing bot
arXiv:2604.18152v1 Announce Type: cross Abstract: Deep learning (DL) has become a cornerstone of modern machine learning (ML) praxis. We introduce the R package mlr3torch, which is an extensible DL fr
arXiv:2604.17245v1 Announce Type: new Abstract: High-DOF dexterous hands require compact actuation, rich sensing, and reliable thermal behavior, but conventional designs often occupy valuable in-hand
arXiv:2604.18164v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have been increasingly used as automatic evaluators-a paradigm known as MLLM-as-a-Judge. However, their reliabi
arXiv:2601.03331v2 Announce Type: replace Abstract: Recent advances in Vision-Language Models (VLMs) have improved performance in multi-modal learning, raising the question of whether these models tru
arXiv:2604.16943v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown impressive capabilities, yet they often struggle to effectively capture the fine-grained textual inf
arXiv:2604.17007v1 Announce Type: new Abstract: Mobile deployment of facial age estimation requires models that balance predictive accuracy with low latency and compact size. In this work, we present
arXiv:2601.21257v2 Announce Type: replace Abstract: Advancing beyond single monolithic language models (LMs), recent research increasingly recognizes the importance of model collaboration, where multi
arXiv:2604.18226v1 Announce Type: new Abstract: Automated analysis of customer feedback on social media is hindered by three challenges: the high cost of annotated training data, the scarcity of evalu
arXiv:2604.16808v1 Announce Type: new Abstract: Current lip-sync deepfake detectors rely on pixel-level artifacts or audio-visual correspondence, failing to generalize across languages because these c
arXiv:2604.17199v1 Announce Type: new Abstract: Dielectric elastomer actuators (DEAs) have garnered extensive attention especially in soft robotic applications over the past few decades owing to the a
arXiv:2604.17713v1 Announce Type: new Abstract: Resting-state functional magnetic resonance imaging (fMRI) has emerged as a cornerstone for psychiatric diagnosis, yet most approaches rely on pairwise
arXiv:2604.18069v1 Announce Type: new Abstract: Humans often hold different perspectives on the same issues. In many NLP tasks, annotation disagreement can reflect valid subjective perspectives. Model
arXiv:2604.17174v1 Announce Type: new Abstract: Modeling human cognitive states is essential for advanced artificial intelligence. Existing Large Language Models (LLMs) mainly address isolated tasks s
arXiv:2604.17972v1 Announce Type: new Abstract: Emotional Support Conversation (ESC) aims to assist individuals experiencing distress by generating empathetic and supportive dialogue. While prior work
arXiv:2604.16419v1 Announce Type: cross Abstract: Fairness-aware recommender systems often mitigate bias by increasing exposure to under-represented or long-tail content, commonly through mechanisms t
arXiv:2604.16461v1 Announce Type: cross Abstract: Physics-guided sampling with diffusion priors has recently shown strong performance in solving complex systems of partial differential equations (PDEs
arXiv:2511.20853v3 Announce Type: replace Abstract: Reliable depth estimation under real optical conditions remains a core challenge for camera vision in systems such as autonomous robotics and augmen
arXiv:2604.18146v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have advanced recommendation systems (RSs), and recent works have begun to explore how to integrate LLMs into i
arXiv:2604.17695v1 Announce Type: cross Abstract: KV cache memory is the dominant bottleneck for long-context LLM inference. Existing compression methods each act on a single axis of the four-dimensio
arXiv:2501.12281v2 Announce Type: replace Abstract: Given a partially observed road network, how can we predict the traffic state of interested unobserved locations? Traffic prediction is crucial for
Managed vulnerability management service startup Mondoo Inc. today announced the launch of Mondoo AI Skills Check, a free security checker designed to address the growing supply chain risk posed by AI
arXiv:2604.17354v1 Announce Type: new Abstract: Vision-Language Models (VLMs) excel at photorealistic generation, yet often struggle to represent abstract meaning such as idiomatic interpretations of
arXiv:2603.21298v2 Announce Type: replace Abstract: Combating hate speech on social media is critical for securing cyberspace, yet relies heavily on the efficacy of automated detection systems. As con
arXiv:2603.19044v2 Announce Type: replace Abstract: Scientific ideation aims to propose novel solutions within a given scientific context. Existing LLM-based agentic approaches emulate human research
arXiv:2604.16503v1 Announce Type: new Abstract: Training strong video generation models usually requires massive datasets, large parameter counts, and substantial compute. In this work, we ask whether
arXiv:2604.17062v1 Announce Type: new Abstract: Zero-shot action recognition is challenging due to the semantic gap between seen and unseen classes. We present a novel framework that enhances CLIP wit
arXiv:2604.17435v1 Announce Type: new Abstract: Recent Speech-to-Speech Translation (S2ST) systems achieve strong semantic accuracy yet consistently strip away non-verbal vocalizations (NVs), such as
As AI assistants and privacy proxies challenge the capabilities of traditional bot detection, the Web needs new models for accountability. We believe that control should remain with the client, and th
Mozilla used Anthropic's Claude Mythos Preview AI to discover 271 vulnerabilities in Firefox 150 , which the company has patched in the browser . The AI was able to reason through code and surface iss
arXiv:2510.12831v3 Announce Type: replace Abstract: Multi-turn Text-to-SQL aims to translate a user's conversational utterances into executable SQL while preserving dialogue coherence and grounding to
arXiv:2604.17965v1 Announce Type: new Abstract: Generalizable Neural Radiance Fields (GeNeRFs) enable high-quality scene reconstruction from sparse views and can generalize to unseen scenes. However,
arXiv:2604.18583v1 Announce Type: new Abstract: Building photorealistic, animatable full-body digital humans remains a longstanding challenge in computer graphics and vision. Recent advances in animat
// Multi-Agent Synthesis RAG // Nice paper on improving RAG systems with multiple agents. (bookmark it) The paper introduces MASS-RAG, a multi-agent synthesis framework for retrieval-augmented generat
arXiv:2310.07464v2 Announce Type: replace-cross Abstract: Biomarker detection is an indispensable part of the diagnosis and treatment of low-grade glioma (LGG). However, current LGG biomarker detectio
arXiv:2604.17567v1 Announce Type: new Abstract: Multi-camera systems are widely employed in sports to capture the 3D motion of athletes and equipment, yet calibrating their extrinsic parameters remain
arXiv:2604.16468v1 Announce Type: new Abstract: Accurate phase equilibria are foundational to alloy design because they encode the underlying thermodynamics governing stability, transformations, and p
arXiv:2604.18477v1 Announce Type: new Abstract: Biological classification with interpretability remains a challenging task. For this, we introduce a novel encoding framework, Multi-Scale Reversible Ch
arXiv:2604.16962v1 Announce Type: new Abstract: Generating trajectories for synthetic aperture radar (SAR)-equipped aircraft poses significant challenges due to terrain constraints, and the need for s
arXiv:2604.18019v1 Announce Type: new Abstract: Sketch-based 3D shape retrieval (SBSR) aims to retrieve 3D shapes that are consistent with the category of the input hand-drawn sketch. The core challen
arXiv:2604.16577v1 Announce Type: new Abstract: Human activity recognition (HAR) refers to the process of identifying human actions and activities using data collected from sensors. Neural networks, s
arXiv:2604.18347v1 Announce Type: new Abstract: Vision Language Models (VLMs) achieved rapid progress in the recent years. However, despite their growth, VLMs development is heavily grounded on Englis
arXiv:2604.16311v1 Announce Type: new Abstract: Automated Fact-Checking (AFC) relies on claim extraction as a first step, yet existing methods largely overlook the multimodal nature of today's misinfo
arXiv:2604.17122v1 Announce Type: new Abstract: Breast cancer is a leading cause of cancer-related mortality worldwide, and timely accurate diagnosis is critical to improving survival outcomes. While
arXiv:2601.05707v2 Announce Type: replace Abstract: Automatic speech recognition (ASR) still covers only a small fraction of the world's languages, mainly due to supervised data scarcity. In-context l
arXiv:2510.09474v2 Announce Type: replace Abstract: Modern conversational agents like ChatGPT and Alexa+ rely on predefined policies specifying metadata, response styles, and tool-usage rules. As thes
arXiv:2401.10747v5 Announce Type: replace-cross Abstract: Multimodal sentiment analysis aims to identify the emotions expressed by individuals through visual, language, and acoustic cues. However, mos
arXiv:2604.18203v1 Announce Type: new Abstract: Multimodal LLMs can accurately perceive numerical content across modalities yet fail to perform exact multi-digit multiplication when the identical unde
arXiv:2604.18564v1 Announce Type: new Abstract: Video world models have achieved remarkable success in simulating environmental dynamics in response to actions by users or agents. They are modeled as
arXiv:2604.18090v1 Announce Type: new Abstract: Functional magnetic composites capable of large deformation, load bearing, and multifunctional motion are essential for next-generation adaptive soft ro
arXiv:2505.20715v2 Announce Type: replace-cross Abstract: Video temporal understanding is crucial for multimodal large language models (MLLMs) to reason over events in videos. Despite recent advances
arXiv:2603.20187v2 Announce Type: replace Abstract: Video-driven human reaction generation aims to synthesize 3D human motions that directly react to observed video sequences, which is crucial for bui
Harmattan is a Paris-based military drone company that produces more than quadcopters, according to a post by AI researcher François Chollet. The company's product line extends beyond standard quadrot
My hunch for now is that this was an ill-considered test which they didn't anticipate would be instantly spotted and cause (justified) uproar - here's hoping they decide that the 'test' isn't a good i
My most popular AI post was a bunch of made-up 'graphs' four years ago. Now, the new GPT-2 image generator does it for real (though not perfect) Here's the famous AI task horizons graph with a touch o